INDEX

Explanations

phrases indicating certainty or emphasis

oai_token-act-pair · gpt-3.5-turbo

assertions or statements about certainty and opinions

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

ivery

-0.78

pak

-0.76

cul

-0.74

minist

-0.73

NetMessage

-0.72

 expend

-0.72

robe

-0.71

endars

-0.70

ãĥīãĥ©ãĤ´ãĥ³

-0.68

ð

-0.67

POSITIVE LOGITS

 bothers

0.81

 seems

0.79

 stands

0.77

 stood

0.75

 remains

0.74

 begs

0.73

 happened

0.72

 mattered

0.71

 suffice

0.71

 holds

0.70

Activations Density 0.052%

phrases indicating certainty or emphasis

assertions or statements about certainty and opinions

No Comments

No Known Activations