INDEX

Explanations

phrases related to involvement or participation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating participation or involvement in activities

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

overe

-0.69

ek

-0.68

 survived

-0.68

aut

-0.66

 bene

-0.65

nor

-0.65

Interstitial

-0.64

theless

-0.63

lect

-0.61

ieth

-0.61

POSITIVE LOGITS

OOL

0.80

Rid

0.74

 groove

0.69

 sidx

0.68

LET

0.67

retty

0.64

skirts

0.63

 snipp

0.63

 dirty

0.62

 jams

0.61

Activations Density 0.191%

phrases related to involvement or participation

phrases indicating participation or involvement in activities

No Comments

No Known Activations