INDEX

Explanations

proper nouns related to specific locations or characters

oai_token-act-pair · gpt-3.5-turbo

variants of the word "care."

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

oret

-0.66

iable

-0.66

UE

-0.62

OD

-0.61

ODE

-0.60

ured

-0.59

PNG

-0.59

razen

-0.59

uration

-0.59

 retrieving

-0.58

POSITIVE LOGITS

tsky

0.91

paren

0.91

fare

0.84

zan

0.81

nea

0.80

rils

0.79

yout

0.79

mares

0.79

butt

0.78

cue

0.77

Activations Density 0.028%

proper nouns related to specific locations or characters

variants of the word "care."

No Comments

No Known Activations