INDEX

Explanations

phrases indicating something is being evaluated, judged, or contemplated

oai_token-act-pair · gpt-3.5-turbo

statements that describe something as being viewed or judged in a certain way

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inas

-0.73

hire

-0.73

dayName

-0.71

cies

-0.63

ciating

-0.63

mouth

-0.63

brow

-0.62

 bombard

-0.62

 Tale

-0.60

LET

-0.59

POSITIVE LOGITS

phas

0.98

 favorably

0.84

 infall

0.77

 synonymous

0.75

 "$:/

0.75

ophile

0.75

 worthy

0.75

 expend

0.74

 taboo

0.73

 Tradable

0.73

Activations Density 0.032%

phrases indicating something is being evaluated, judged, or contemplated

statements that describe something as being viewed or judged in a certain way

No Comments

No Known Activations