INDEX

Explanations

phrases related to actions or events involving individuals or groups

oai_token-act-pair · gpt-3.5-turbo

references to law enforcement, violence, and familial relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.71

angan

-0.63

 antid

-0.62

 preventive

-0.61

 Recomm

-0.60

 sugg

-0.59

iru

-0.59

 fundament

-0.59

ufact

-0.58

 Dietary

-0.58

POSITIVE LOGITS

 unfold

1.11

 firsthand

0.82

 crumble

0.80

 grow

0.77

amorph

0.77

 afar

0.74

 shrink

0.71

aily

0.70

 emerge

0.70

 slide

0.70

Activations Density 0.603%

phrases related to actions or events involving individuals or groups

references to law enforcement, violence, and familial relationships

No Comments

No Known Activations