INDEX

Explanations

introductory phrases indicating a new topic or section

oai_token-act-pair · gpt-3.5-turbo

sections that introduce content or provide context in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Strait

-0.60

 sshd

-0.59

natureconservancy

-0.59

)].

-0.56

mong

-0.56

EStreamFrame

-0.55

 absor

-0.54

TPPStreamerBot

-0.54

 systemd

-0.53

ãĤ£

-0.53

POSITIVE LOGITS

tical

1.30

tics

1.29

abouts

1.28

tic

1.02

upon

0.96

after

0.86

fore

0.85

with

0.82

eren

0.77

 Comes

0.76

Activations Density 0.042%

introductory phrases indicating a new topic or section

sections that introduce content or provide context in a document

No Comments

No Known Activations