INDEX

Explanations

words related to baseball, sports, and specific names

oai_token-act-pair · gpt-3.5-turbo

information about sports and athletes

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

inational

-0.53

 innovative

-0.51

 economically

-0.50

 compelling

-0.49

 indigenous

-0.47

 incumbent

-0.47

 globally

-0.47

 amid

-0.46

 multinational

-0.46

 southeastern

-0.46

POSITIVE LOGITS

xual

0.60

girl

0.56

fuck

0.55

EEEE

0.55

~~~~

0.54

iatus

0.53

...?

0.53

ITNESS

0.52

!!!!!

0.52

wagon

0.52

Activations Density 3.111%

words related to baseball, sports, and specific names

information about sports and athletes

No Comments

No Known Activations