INDEX

Explanations

years represented in the format 'YYYY'

oai_token-act-pair · gpt-3.5-turbo

references to specific years or dates

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

lass

-0.79

 stead

-0.78

amber

-0.77

hed

-0.75

ess

-0.73

kell

-0.70

esses

-0.70

iqu

-0.70

estine

-0.69

terday

-0.69

POSITIVE LOGITS

å¹

1.43

å¤©

0.85

 Edition

0.82

-'

0.77

 edition

0.76

 EDITION

0.76

 Nobel

0.75

âĢ²

0.75

 vintage

0.74

 Remastered

0.72

Activations Density 0.110%

years represented in the format 'YYYY'

references to specific years or dates

No Comments

No Known Activations