INDEX

Explanations

words related to physical actions involving force or impact

oai_token-act-pair · gpt-3.5-turbo

verbs related to physical actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

[*]

-0.69

Yen

-0.66

 Leilan

-0.66

CBI

-0.62

åĭ

-0.61

Nem

-0.59

USC

-0.59

DragonMagazine

-0.57

SAR

-0.56

 Hermes

-0.55

POSITIVE LOGITS

waukee

0.97

emonic

0.89

ographed

0.87

ochond

0.85

aukee

0.83

achusetts

0.83

ogi

0.80

omatic

0.79

imore

0.76

gage

0.74

Activations Density 0.088%

words related to physical actions involving force or impact

verbs related to physical actions or processes

No Comments

No Known Activations