INDEX

Explanations

instances where someone is explaining or noting something to others

oai_token-act-pair · gpt-3.5-turbo

instances where explanations and assertions are being made

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

Ther

-0.65

raq

-0.59

held

-0.56

peg

-0.56

respect

-0.55

icum

-0.54

bish

-0.54

backer

-0.53

aic

-0.53

Pont

-0.53

POSITIVE LOGITS

©¶æ

0.84

 "âĢ¦

0.83

"[

0.81

 "...

0.81

-+-+

0.71

'[

0.70

"(

0.69

=\"

0.67

 quoting

0.65

 although

0.64

Activations Density 0.257%

instances where someone is explaining or noting something to others

instances where explanations and assertions are being made

No Comments

No Known Activations