INDEX

Explanations

words related to titles or names ending in "anc"

oai_token-act-pair · gpt-3.5-turbo

proper nouns or specific names

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

ãĥīãĥ©

-0.80

ĪĴ

-0.79

ãĢĲ

-0.68

åĤ

-0.68

nings

-0.66

knife

-0.66

 Gors

-0.66

 Fraz

-0.64

 IMAGES

-0.63

nces

-0.63

POSITIVE LOGITS

orp

1.04

ourt

1.01

uten

0.92

ulty

0.92

ipation

0.89

eteria

0.88

isco

0.88

ultural

0.88

risis

0.84

henko

0.83

Activations Density 0.018%

words related to titles or names ending in "anc"

proper nouns or specific names

No Comments

No Known Activations