INDEX

Explanations

dates and months mentioned in documents

oai_token-act-pair · gpt-3.5-turbo

references to specific months

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

 Haram

-0.85

otle

-0.77

anooga

-0.74

aque

-0.73

ioch

-0.71

enh

-0.69

oos

-0.69

emort

-0.69

leck

-0.68

gers

-0.68

POSITIVE LOGITS

ths

0.85

pring

0.81

 Ukrain

0.81

 Ples

0.80

nd

0.75

flower

0.75

itime

0.71

theless

0.71

iversary

0.71

rences

0.70

Activations Density 0.068%

dates and months mentioned in documents

references to specific months

No Comments

No Known Activations