INDEX

Explanations

football teams along with some specific years and places

oai_token-act-pair · gpt-3.5-turbo

names of sports teams and geographic locations

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

minist

-0.62

rodu

-0.59

 constitu

-0.57

Reviewer

-0.54

agonist

-0.53

 pione

-0.52

uscript

-0.51

 opin

-0.51

efficients

-0.50

xual

-0.50

POSITIVE LOGITS

.>>

0.57

isi

0.54

boro

0.53

BSD

0.52

/.

0.52

 sockets

0.50

/?

0.50

esque

0.50

kies

0.49

/*

0.49

Activations Density 0.850%

football teams along with some specific years and places

names of sports teams and geographic locations

No Comments

No Known Activations