INDEX

Explanations

phrases indicating a desire or intention to do something

oai_token-act-pair · gpt-3.5-turbo

expressions of desire or intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

stand

-0.67

bug

-0.65

ibliography

-0.64

trust

-0.64

aka

-0.61

 Â®

-0.60

alias

-0.60

voc

-0.59

manship

-0.59

iop

-0.57

POSITIVE LOGITS

 clarification

0.79

 revenge

0.77

to

0.72

 something

0.71

 answers

0.66

 permission

0.66

 clarity

0.64

 desperately

0.61

 attention

0.61

":[{"

0.60

Activations Density 0.093%

phrases indicating a desire or intention to do something

expressions of desire or intention

No Comments

No Known Activations