INDEX

Explanations

specific names of places or people

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

onz

-0.93

sburgh

-0.86

arcer

-0.85

onder

-0.78

olkien

-0.75

idious

-0.75

ailand

-0.74

ocaust

-0.73

okemon

-0.72

reek

-0.72

POSITIVE LOGITS

 Song

0.80

 Swan

0.79

 Ding

0.79

apple

0.79

 Basin

0.77

Lake

0.76

phase

0.76

 PsyNet

0.76

 Stab

0.75

 Lake

0.75

Activations Density 0.042%

specific names of places or people

proper nouns, particularly names of people and places

No Comments

No Known Activations