INDEX

Explanations

statements expressing support or validation

oai_token-act-pair · gpt-3.5-turbo

phrases related to support or validation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

nel

-0.75

anny

-0.73

ities

-0.70

 newsp

-0.69

pox

-0.68

inational

-0.65

 Hebdo

-0.65

 irony

-0.64

entric

-0.63

 ILCS

-0.63

POSITIVE LOGITS

raise

0.75

hard

0.75

track

0.73

byn

0.73

abies

0.71

drive

0.69

ament

0.67

taking

0.66

GROUND

0.65

lash

0.65

Activations Density 0.038%

statements expressing support or validation

phrases related to support or validation

No Comments

No Known Activations