INDEX

Explanations

proper names followed by speech or dialogue

oai_token-act-pair · gpt-3.5-turbo

repeated use of commas in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

olves

-0.59

 obscurity

-0.59

swick

-0.59

eers

-0.58

izon

-0.57

Kind

-0.56

 breakthrough

-0.56

 trouble

-0.55

 consequential

-0.54

case

-0.54

POSITIVE LOGITS

"[

0.95

 "âĢ¦

0.91

"(

0.89

 "...

0.89

'[

0.87

"'

0.83

"{

0.81

"@

0.79

 citing

0.78

"$

0.76

Activations Density 0.121%

proper names followed by speech or dialogue

repeated use of commas in sentences

No Comments

No Known Activations