INDEX

Explanations

phrases indicating a wise or probably successful choice of action

oai_token-act-pair · gpt-3.5-turbo

references to good ideas or suggestions

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

ancies

-0.84

wagen

-0.76

atson

-0.69

doms

-0.68

apons

-0.67

yss

-0.65

 clipboard

-0.65

isner

-0.65

dust

-0.65

chem

-0.63

POSITIVE LOGITS

wark

0.80

ATIVE

0.73

ãĤ¢ãĥ«

0.73

================

0.69

isphere

0.67

 approximation

0.67

âĶģ

0.65

idon

0.64

 considering

0.63

ï

0.63

Activations Density 0.145%

phrases indicating a wise or probably successful choice of action

references to good ideas or suggestions

No Comments

No Known Activations