INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

the end of the 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

ãĥ¼ãĥĨ

-0.84

enegger

-0.80

 Thumbnails

-0.68

 Vaugh

-0.61

mercial

-0.61

espie

-0.60

 destro

-0.58

EStream

-0.58

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.56

CLASSIFIED

-0.56

POSITIVE LOGITS

anta

0.82

ip

0.78

ax

0.71

isha

0.70

aj

0.68

oton

0.68

ona

0.67

anton

0.65

iph

0.65

ifa

0.65

Activations Density 0.420%

names of individuals

the end of the document

No Comments

No Known Activations