INDEX

Explanations

phrases indicating judgment or value attribution

oai_token-act-pair · gpt-3.5-turbo

instances of the word "that."

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

 Pets

-0.78

 Cheong

-0.74

hips

-0.72

 Directions

-0.68

ãĥ¥

-0.68

 Gallery

-0.65

 Cong

-0.64

 Cards

-0.64

 Planning

-0.63

raq

-0.62

POSITIVE LOGITS

 satisfies

0.82

 violates

0.82

 consumes

0.81

 preceded

0.79

 resembles

0.74

ĨĴ

0.74

 produces

0.73

¥µ

0.72

cedes

0.72

 involves

0.71

Activations Density 0.240%

phrases indicating judgment or value attribution

instances of the word "that."

No Comments

No Known Activations