INDEX

Explanations

references to the concept of "handedness", specifically the term "handed" with high activation values

oai_token-act-pair · gpt-3.5-turbo

references to handedness, particularly in relation to left-handedness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ouf

-0.73

lÃ©

-0.70

LAN

-0.68

 Delta

-0.68

CHAT

-0.68

 Detect

-0.68

 Scores

-0.66

Eps

-0.66

Tonight

-0.66

ETF

-0.66

POSITIVE LOGITS

handed

1.31

 nodd

1.07

maid

0.92

 showc

0.88

footed

0.85

hander

0.82

 destro

0.82

 enthusi

0.79

axe

0.78

ragon

0.77

Activations Density 0.007%

references to the concept of "handedness", specifically the term "handed" with high activation values

references to handedness, particularly in relation to left-handedness

No Comments

No Known Activations