INDEX

Explanations

instances of the word "lesser" appearing in the text

oai_token-act-pair · gpt-3.5-turbo

references to things described as "lesser" or of lower significance or status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

eston

-0.63

APP

-0.60

!!

-0.60

storm

-0.58

Â®

-0.56

Trans

-0.56

 Update

-0.56

 Updates

-0.56

aeus

-0.54

tx

-0.54

POSITIVE LOGITS

 lesser

3.69

 smaller

1.50

 weaker

1.43

 greater

1.29

 shorter

1.18

 inferior

1.16

 finer

1.15

 less

1.14

 lighter

1.12

 Less

1.09

Activations Density 0.011%

instances of the word "lesser" appearing in the text

references to things described as "lesser" or of lower significance or status

No Comments

No Known Activations