INDEX

Explanations

legal terms or references, specifically related to various legal codes or regulations

oai_token-act-pair · gpt-3.5-turbo

references to legal codes or regulations

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

swer

-0.91

ties

-0.82

 Ples

-0.78

esville

-0.75

 experien

-0.75

jen

-0.70

innie

-0.69

 Democr

-0.67

eatures

-0.67

ishly

-0.66

POSITIVE LOGITS

 snippet

0.88

otle

0.83

book

0.76

 breaths

0.75

 breath

0.74

 enforced

0.73

 Compliance

0.72

breaker

0.71

 breaker

0.69

 codes

0.68

Activations Density 0.015%

legal terms or references, specifically related to various legal codes or regulations

references to legal codes or regulations

No Comments

No Known Activations