INDEX

Explanations

names of individuals with their corresponding relevance levels

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 womb

-0.64

Ont

-0.61

etheless

-0.61

 chem

-0.60

ĪĴ

-0.60

ModLoader

-0.58

 zoning

-0.57

PsyNetMessage

-0.57

USC

-0.56

 soluble

-0.55

POSITIVE LOGITS

arde

0.91

ĳå£«

0.87

igl

0.83

izo

0.79

assi

0.76

idy

0.76

 apologised

0.75

ource

0.71

oute

0.70

itan

0.70

Activations Density 0.087%

names of individuals with their corresponding relevance levels

proper nouns, particularly names of individuals

No Comments

No Known Activations