INDEX

Explanations

proper nouns related to specific individuals or entities

oai_token-act-pair · gpt-3.5-turbo

names and terms related to specific characters or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Gear

-0.81

dylib

-0.80

jj

-0.76

-0.75

-0.73

rette

-0.73

-0.72

 Vessel

-0.72

Dew

-0.71

POSITIVE LOGITS

an

1.53

AN

1.43

pan

1.29

anon

1.23

kan

1.23

Pan

1.22

ans

1.22

anan

1.20

Ran

1.18

 Anon

1.18

Activations Density 0.253%

proper nouns related to specific individuals or entities

names and terms related to specific characters or entities

No Comments

No Known Activations