INDEX

Explanations

instances of legal action, specifically lawsuits

oai_token-act-pair · gpt-3.5-turbo

instances of the word "sue" and its variations

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

atomic

-0.78

obyl

-0.78

acho

-0.74

lot

-0.74

existent

-0.72

adden

-0.70

translation

-0.70

adequ

-0.69

nown

-0.69

apo

-0.69

POSITIVE LOGITS

 suing

0.92

 against

0.88

sue

0.86

 sued

0.84

him

0.71

 Hansen

0.69

 Gloria

0.69

 anonymously

0.68

AGA

0.66

 Judd

0.66

Activations Density 0.027%

instances of legal action, specifically lawsuits

instances of the word "sue" and its variations

No Comments

No Known Activations