INDEX

Explanations

pronouns or references to people other than the speaker

oai_token-act-pair · gpt-3.5-turbo

references to the collective experience of others

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

omorph

-0.73

forestation

-0.69

tein

-0.68

Accessory

-0.64

orno

-0.63

nec

-0.63

BTC

-0.61

osterone

-0.61

height

-0.60

Runner

-0.60

POSITIVE LOGITS

 describ

0.83

 besides

0.76

 afforded

0.75

 else

0.75

 behaved

0.74

Joined

0.73

 succumbed

0.71

 includ

0.71

who

0.71

 subjected

0.70

Activations Density 0.014%

pronouns or references to people other than the speaker

references to the collective experience of others

No Comments

No Known Activations