INDEX

Explanations

verbs related to taking action or making decisions

oai_token-act-pair · gpt-3.5-turbo

imperative phrases that express necessity or obligation

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

 addictive

-0.66

 Levant

-0.65

bone

-0.65

ELD

-0.63

chy

-0.59

 Marino

-0.58

Dro

-0.57

Favorite

-0.57

 epile

-0.57

cit

-0.57

POSITIVE LOGITS

 ourselves

1.16

 educate

0.83

 conclude

0.82

 discuss

0.82

 celebrate

0.81

ruce

0.81

yt

0.76

 collectively

0.76

 presume

0.76

 learn

0.76

Activations Density 0.216%

verbs related to taking action or making decisions

imperative phrases that express necessity or obligation

No Comments

No Known Activations