INDEX

Explanations

legal and administrative terms related to licensing and regulations

oai_token-act-pair · gpt-3.5-turbo

terms related to authority and organizational structures

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

£ı

-0.65

keyes

-0.60

Ô

-0.60

hower

-0.57

çĭ

-0.56

yss

-0.55

Gaming

-0.54

Īè

-0.54

href

-0.54

 Justice

-0.53

POSITIVE LOGITS

 pamph

0.58

atcher

0.57

 extraord

0.56

 inhal

0.54

esses

0.53

ivals

0.52

idon

0.52

 guru

0.51

 certification

0.51

ournals

0.51

Activations Density 0.619%

legal and administrative terms related to licensing and regulations

terms related to authority and organizational structures

No Comments

No Known Activations