INDEX

Explanations

online-related phrases

oai_token-act-pair · gpt-3.5-turbo

references to the word "both" or its context in discussions of dualities or comparisons

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

 Parables

-0.71

 discont

-0.64

 Collider

-0.59

 Picks

-0.59

 extrad

-0.58

 Caption

-0.58

 Wire

-0.57

 Screw

-0.56

 Petition

-0.56

 charism

-0.56

POSITIVE LOGITS

 sexes

1.03

"]=>

0.80

nor

0.80

alde

0.75

 genders

0.70

 statically

0.69

ãĥ¬

0.66

icable

0.66

desktop

0.63

fml

0.62

Activations Density 0.130%

online-related phrases

references to the word "both" or its context in discussions of dualities or comparisons

No Comments

No Known Activations