INDEX

Explanations

instances of the word "liability"

oai_token-act-pair · gpt-3.5-turbo

terms and concepts related to liability and legal responsibility

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

urations

-0.90

rica

-0.87

etus

-0.85

tons

-0.84

rient

-0.83

efully

-0.82

furt

-0.81

ovie

-0.81

erva

-0.79

anooga

-0.79

POSITIVE LOGITS

 liability

1.06

 forgiven

0.88

 liabilities

0.86

 indemn

0.86

 incurred

0.79

 insurance

0.78

 issuer

0.76

 bracket

0.69

BILITY

0.69

 damages

0.67

Activations Density 0.023%

instances of the word "liability"

terms and concepts related to liability and legal responsibility

No Comments

No Known Activations