INDEX

Explanations

phrases that suggest or hint at something without explicitly stating it

oai_token-act-pair · gpt-3.5-turbo

expressions of suggestion or inference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

mir

-0.83

 Reds

-0.76

thumbnails

-0.74

Ern

-0.73

ÄŁ

-0.71

unker

-0.64

dan

-0.62

agra

-0.62

home

-0.61

 Nanto

-0.60

POSITIVE LOGITS

 imply

0.97

 implied

0.95

 WARRANT

0.82

 implies

0.82

antle

0.79

 guiActiveUn

0.77

DonaldTrump

0.76

 infer

0.74

 implying

0.73

LY

0.71

Activations Density 0.020%

phrases that suggest or hint at something without explicitly stating it

expressions of suggestion or inference

No Comments

No Known Activations