INDEX

Explanations

statistics and figures

oai_token-act-pair · gpt-3.5-turbo

expressions related to political events or groups

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

 ..."

-0.64

 Allaah

-0.55

-->

-0.55

.</

-0.54

...)

-0.54

`.

-0.54

.","

-0.54

Allah

-0.53

``(

-0.52

.<

-0.51

POSITIVE LOGITS

 meanwhile

0.66

odore

0.59

endum

0.52

 Jacobs

0.48

ccording

0.47

 irony

0.47

 however

0.46

 Lauder

0.46

 responded

0.46

 aback

0.45

Activations Density 1.792%

statistics and figures

expressions related to political events or groups

No Comments

No Known Activations