INDEX

Explanations

words related to financial or legal contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to collateral damage and associated medical or legal implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tower

-0.96

stakes

-0.89

houses

-0.86

eled

-0.86

oak

-0.85

oslav

-0.83

house

-0.79

soDeliveryDate

-0.79

maker

-0.77

nen

-0.75

POSITIVE LOGITS

ateral

1.05

ities

0.86

 collateral

0.84

 sclerosis

0.82

 prefrontal

0.80

 Sins

0.78

ization

0.76

lig

0.73

izable

0.72

 comprom

0.72

Activations Density 0.060%

words related to financial or legal contexts

terms related to collateral damage and associated medical or legal implications

No Comments

No Known Activations