INDEX

Explanations

references to illegality or illegal actions

oai_token-act-pair · gpt-3.5-turbo

terms related to illegality and delegation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 wounds

-0.76

uyomi

-0.75

âķĲâķĲ

-0.72

Ward

-0.67

âķĲ

-0.66

anwhile

-0.66

 breath

-0.64

 rift

-0.64

akening

-0.63

 Nile

-0.63

POSITIVE LOGITS

 illeg

0.98

ibility

0.95

acies

0.93

ality

0.92

matical

0.92

itimate

0.91

itives

0.90

ible

0.90

acy

0.88

ials

0.88

Activations Density 0.015%

references to illegality or illegal actions

terms related to illegality and delegation

No Comments

No Known Activations