INDEX

Explanations

mentions of the word "Pixar"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Pixar."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

à¨

-0.71

#$#$

-0.67

 behavi

-0.67

GROUND

-0.67

ANK

-0.66

 silence

-0.65

 captcha

-0.63

lehem

-0.62

INST

-0.60

à©

-0.57

POSITIVE LOGITS

xes

1.20

xus

1.14

edo

1.11

iang

1.04

iao

1.00

avier

0.99

eus

0.98

posure

0.96

aminer

0.92

ipl

0.90

Activations Density 0.033%

mentions of the word "Pixar"

mentions of the term "Pixar."

No Comments

No Known Activations