INDEX

Explanations

text within square brackets that express opinions or attributions

oai_token-act-pair · gpt-3.5-turbo

quoted speech or dialogue within the text

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

 Tang

-0.59

 Miss

-0.55

 Lens

-0.53

 Rider

-0.53

 family

-0.53

 Gate

-0.52

 normal

-0.51

 castle

-0.50

âĢĲ

-0.48

POSITIVE LOGITS

"[

2.82

"[

2.60

"(

1.89

'[

1.74

"(

1.71

"'

1.65

 "âĢ¦

1.52

"{

1.50

"#

1.48

 "...

1.45

Activations Density 0.018%

text within square brackets that express opinions or attributions

quoted speech or dialogue within the text

No Comments

No Known Activations