INDEX

Explanations

adjectives expressing strong opinions on actions or events

oai_token-act-pair · gpt-3.5-turbo

strong negative sentiments and descriptions of unacceptable behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

asio

-0.68

lur

-0.64

 selves

-0.62

 wills

-0.62

essor

-0.61

 Flavoring

-0.59

animate

-0.59

ioxide

-0.58

 masters

-0.58

omething

-0.57

POSITIVE LOGITS

 overdue

0.78

 considering

0.74

"[

0.73

amount

0.70

''

0.68

 akin

0.68

 because

0.68

 retaliation

0.67

iev

0.67

.[

0.66

Activations Density 0.471%

adjectives expressing strong opinions on actions or events

strong negative sentiments and descriptions of unacceptable behavior

No Comments

No Known Activations