INDEX

Explanations

phrases related to news headlines

oai_token-act-pair · gpt-3.5-turbo

instances of dashes or other symbols indicating breaks in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

wagen

-0.79

spir

-0.65

deals

-0.64

interstitial

-0.64

 servicing

-0.63

bour

-0.62

stones

-0.62

agate

-0.61

heric

-0.61

range

-0.61

POSITIVE LOGITS

 Comments

0.86

 Advertisement

0.81

=-=-=-=-

0.73

––

0.73

 Transcript

0.71

ADVERTISEMENT

0.70

 Fever

0.69

=-=-=-=-=-=-=-=-

0.68

Edited

0.68

ĸļ

0.66

Activations Density 0.049%

phrases related to news headlines

instances of dashes or other symbols indicating breaks in text

No Comments

No Known Activations