INDEX

Explanations

proper nouns or names that are associated with different events or people, especially those related to interviews or collaborations

oai_token-act-pair · gpt-3.5-turbo

the word "for" used in various contexts

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

Negative Logits

ttle

-0.72

aults

-0.70

Fle

-0.68

plate

-0.64

fleet

-0.64

hess

-0.63

Ohio

-0.62

illin

-0.62

Strange

-0.62

Â§

-0.61

POSITIVE LOGITS

geries

1.22

 example

1.05

ked

1.03

bidden

1.01

 instance

0.98

gery

0.96

 purposes

0.89

gotten

0.83

 centuries

0.83

 whom

0.79

Activations Density 0.275%

proper nouns or names that are associated with different events or people, especially those related to interviews or collaborations

the word "for" used in various contexts

No Known Activations