INDEX

Explanations

phrases indicating importance or significance

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "and" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LOCK

-0.72

YP

-0.71

Ĥİ

-0.70

Shut

-0.69

uta

-0.66

STE

-0.66

è»

-0.65

Cub

-0.64

lace

-0.63

Els

-0.62

POSITIVE LOGITS

 hence

1.40

 consequently

1.35

 therefore

1.35

 thus

1.23

 secondly

1.13

 furthermore

1.04

 thereby

1.02

 moreover

1.00

 then

0.94

 although

0.93

Activations Density 0.670%

phrases indicating importance or significance

the repeated use of the word "and" in various contexts

No Comments

No Known Activations