INDEX

Explanations

instances of the word "inform" and related terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "inform" in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Kings

-0.71

âĻ¥

-0.66

imposed

-0.65

á

-0.63

 vain

-0.62

cdn

-0.62

FUN

-0.61

 Kings

-0.61

DAY

-0.60

mad

-0.60

POSITIVE LOGITS

ally

1.09

tale

0.97

ations

0.89

ificantly

0.86

ingly

0.85

acion

0.85

 inform

0.83

ational

0.80

osc

0.79

ographics

0.78

Activations Density 0.014%

instances of the word "inform" and related terms

occurrences of the word "inform" in various contexts

No Known Activations