INDEX

Explanations

words related to locations or places

oai_token-act-pair · gpt-3.5-turbo

instances of the word "or"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 msec

-0.60

OTAL

-0.60

Fra

-0.60

eas

-0.59

assadors

-0.59

inctions

-0.58

SPONSORED

-0.56

SPA

-0.56

Wall

-0.55

pter

-0.54

POSITIVE LOGITS

ific

1.08

chid

1.06

phans

1.05

izons

1.02

andom

1.00

ussia

0.97

ikawa

0.96

onto

0.95

thodox

0.94

acle

0.90

Activations Density 0.028%

words related to locations or places

instances of the word "or"

No Comments

No Known Activations