INDEX

Explanations

years in the format 'YYYY' that are prominent in a text

oai_token-act-pair · gpt-3.5-turbo

mention of specific years

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

letes

-0.72

hing

-0.62

tro

-0.59

ype

-0.57

hed

-0.56

 VIDEOS

-0.56

hop

-0.55

Liter

-0.55

 phosphate

-0.54

bip

-0.54

POSITIVE LOGITS

ruary

0.79

assetsadobe

0.77

foundland

0.74

furt

0.74

 onwards

0.69

inson

0.67

-'

0.66

ynski

0.65

 Heights

0.65

Activations Density 0.296%

years in the format 'YYYY' that are prominent in a text

mention of specific years

No Known Activations