INDEX

Explanations

terms related to physical locations or attributes, particularly focusing on the concept of a small area or a distinct portion of something

oai_token-act-pair · gpt-3.5-turbo

references to "patch" or "patches" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âĹ¼

-0.74

minist

-0.73

Materials

-0.72

 ministry

-0.70

PUT

-0.69

=-=-=-=-

-0.69

¢

-0.68

 forc

-0.68

Demand

-0.67

 defe

-0.65

POSITIVE LOGITS

ioned

1.04

 patches

0.89

work

0.85

ions

0.85

iness

0.84

ion

0.82

 patch

0.81

aments

0.81

 patched

0.81

 Patch

0.81

Activations Density 0.028%

terms related to physical locations or attributes, particularly focusing on the concept of a small area or a distinct portion of something

references to "patch" or "patches" in various contexts

No Comments

No Known Activations