INDEX

Explanations

names of people or professions

oai_token-act-pair · gpt-3.5-turbo

questions and statements related to accountability and judgment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ARDIS

-0.69

geoning

-0.69

inel

-0.65

hement

-0.61

lesh

-0.61

MFT

-0.60

 incapac

-0.59

=-=-

-0.58

imov

-0.57

abad

-0.57

POSITIVE LOGITS

 doing

1.07

 Doing

1.02

 accomplished

0.98

 done

0.97

 entail

0.96

SourceFile

0.93

 fuss

0.88

 Saying

0.88

 Done

0.87

 entails

0.87

Activations Density 0.607%

names of people or professions

questions and statements related to accountability and judgment

No Comments

No Known Activations