INDEX

Explanations

questions asked in informal conversation

oai_token-act-pair · gpt-3.5-turbo

questions about personal experiences and opinions

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

"],"

-0.71

$$$$

-0.70

 illeg

-0.67

ICT

-0.64

wart

-0.64

seless

-0.64

 SetFontSize

-0.61

pty

-0.60

.")

-0.60

arte

-0.60

POSITIVE LOGITS

 experien

0.86

?:

0.73

 reluct

0.71

 personally

0.69

abis

0.68

?ãĢį

0.68

 autobi

0.68

 challeng

0.67

phrine

0.67

 accomp

0.66

Activations Density 0.372%

questions asked in informal conversation

questions about personal experiences and opinions

No Comments

No Known Activations