INDEX

Explanations

mentions of physical injuries or damage

oai_token-act-pair · gpt-3.5-turbo

instances of the word "torn."

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

VERTISEMENT

-0.77

arten

-0.73

perty

-0.70

alty

-0.70

ITNESS

-0.70

racuse

-0.68

travel

-0.67

lain

-0.67

Technology

-0.66

erver

-0.65

POSITIVE LOGITS

adoes

1.61

ados

1.07

adic

0.87

 estranged

0.77

 torn

0.73

 apart

0.73

 parting

0.71

 exting

0.71

 wounds

0.70

 wrapping

0.70

Activations Density 0.014%

mentions of physical injuries or damage

instances of the word "torn."

No Comments

No Known Activations