INDEX

Explanations

numeric values

oai_token-act-pair · gpt-3.5-turbo

numerical values, particularly years and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

eer

-0.81

eers

-0.76

ei

-0.73

LOAD

-0.73

iard

-0.72

yang

-0.71

geist

-0.71

gie

-0.71

hner

-0.69

izen

-0.68

POSITIVE LOGITS

 ILCS

1.21

ERSON

0.80

 Yard

0.78

ISH

0.77

ishing

0.76

ACP

0.74

%:

0.74

RET

0.70

thal

0.69

rican

0.69

Activations Density 0.093%

numeric values

numerical values, particularly years and measurements

No Comments

No Known Activations