INDEX

Explanations

phrases related to defiance or unwavering determination

oai_token-act-pair · gpt-3.5-turbo

the phrase "no matter what" and its variations

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

ãĥį

-0.85

OL

-0.84

uterte

-0.83

alk

-0.81

\\\\\\\\

-0.80

ahime

-0.79

unn

-0.76

Gene

-0.76

lynn

-0.76

RNA

-0.76

POSITIVE LOGITS

 whatsoever

0.85

 coerc

0.78

 slightest

0.77

 jurisd

0.76

 thickness

0.75

 else

0.74

 confir

0.73

hue

0.71

 fuss

0.70

 challeng

0.70

Activations Density 0.056%

phrases related to defiance or unwavering determination

the phrase "no matter what" and its variations

No Comments

No Known Activations