INDEX

Explanations

verbs indicating actions or states of being that are done or experienced intensively or completely

oai_token-act-pair · gpt-3.5-turbo

words related to leadership or presiding roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atto

-0.79

igslist

-0.59

 Galaxy

-0.58

ilet

-0.57

 Aircraft

-0.57

Hus

-0.54

Ads

-0.54

inyl

-0.54

ilda

-0.53

 reported

-0.53

POSITIVE LOGITS

âĸ¬

0.85

etheless

0.82

Behind

0.76

////////////////////////////////

0.73

atively

0.71

ENCY

0.66

lie

0.65

state

0.65

âĸ¬âĸ¬

0.64

 skelet

0.63

Activations Density 0.141%

verbs indicating actions or states of being that are done or experienced intensively or completely

words related to leadership or presiding roles

No Comments

No Known Activations