INDEX

Explanations

time-related events or changes

oai_token-act-pair · gpt-3.5-turbo

temporal phrases indicating changes over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Ĥª

-0.77

Ļ

-0.77

owship

-0.72

ãĤ¹

-0.65

ģ

-0.65

ĩ

-0.64

 cherished

-0.63

 voic

-0.63

Favorite

-0.62

 Sons

-0.62

POSITIVE LOGITS

 adjusting

0.96

 accounting

0.91

 subtract

0.90

noon

0.78

 excluding

0.76

market

0.75

hattan

0.73

kefeller

0.72

 adjustment

0.71

achev

0.71

Activations Density 0.125%

time-related events or changes

temporal phrases indicating changes over time

No Comments

No Known Activations