INDEX

Explanations

the word "hasn"

oai_token-act-pair · gpt-3.5-turbo

the phrase "hasn't" indicating lack or absence of action or change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tone

-0.65

 Agency

-0.63

ealing

-0.63

 Kills

-0.60

 covers

-0.60

 Dial

-0.60

mens

-0.60

fox

-0.59

angering

-0.58

rone

-0.58

POSITIVE LOGITS

't

1.25

ited

0.91

ajor

0.86

ģĸ

0.86

 been

0.82

¨

0.81

 Been

0.78

kered

0.78

dayName

0.76

geon

0.76

Activations Density 0.009%

the word "hasn"

the phrase "hasn't" indicating lack or absence of action or change

No Comments

No Known Activations