INDEX

Explanations

phrases expressing specificity and directness

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize exactness or specificity in descriptions

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

eka

-0.77

ways

-0.76

Pg

-0.66

bp

-0.64

cler

-0.64

 Bounce

-0.64

uay

-0.63

way

-0.62

 Louie

-0.62

WAYS

-0.62

POSITIVE LOGITS

è¦

0.73

 happened

0.66

 programmed

0.63

 wrong

0.63

irements

0.62

 thrust

0.62

isites

0.62

ãĤ¯

0.62

 scenario

0.61

 guiActiveUn

0.61

Activations Density 0.106%

phrases expressing specificity and directness

phrases that emphasize exactness or specificity in descriptions

No Comments

No Known Activations