INDEX

Explanations

phrases related to physical locations or objects above the ground

oai_token-act-pair · gpt-3.5-turbo

instances of the term 'overhead' 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

ifying

-0.96

ifies

-0.96

ifier

-0.94

ifiable

-0.92

eming

-0.90

ifiers

-0.87

ified

-0.83

orian

-0.79

ELY

-0.77

atche

-0.77

POSITIVE LOGITS

 overhead

1.11

 crane

0.90

 projector

0.78

 lobe

0.74

 fees

0.74

 bins

0.73

cuts

0.72

 flap

0.70

 detach

0.69

lift

0.67

Activations Density 0.019%

phrases related to physical locations or objects above the ground

instances of the term 'overhead' in various contexts

No Comments

No Known Activations