INDEX

Explanations

words or phrases containing the prefix "en"

oai_token-act-pair · gpt-3.5-turbo

forms of the word "en."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Intermediate

-0.65

 independently

-0.59

 overdue

-0.59

 Adults

-0.56

 behind

-0.56

ACY

-0.55

 halfway

-0.55

 inaccurate

-0.55

 Hussein

-0.54

 incorrect

-0.54

POSITIVE LOGITS

 masse

1.31

viron

1.30

cyclop

1.22

igma

1.15

unci

1.15

igm

1.14

quire

1.13

vious

1.13

route

1.13

forcer

1.13

Activations Density 0.016%

words or phrases containing the prefix "en"

forms of the word "en."

No Comments

No Known Activations