INDEX

Explanations

phrases related to secrecy and personal relationships

oai_token-act-pair · gpt-3.5-turbo

phrases related to secretive behavior and personal relationships

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

 GOODMAN

-0.74

espie

-0.70

ATF

-0.66

 NOAA

-0.66

 seism

-0.64

 Heritage

-0.64

 Lands

-0.64

NTS

-0.64

 proponents

-0.64

 Canaver

-0.63

POSITIVE LOGITS

 boyfriend

0.98

 girlfriends

0.91

 boobs

0.90

sexual

0.89

 shit

0.89

 shitty

0.89

 kissing

0.88

 naughty

0.88

 diaper

0.87

 princess

0.87

Activations Density 1.355%

phrases related to secrecy and personal relationships

phrases related to secretive behavior and personal relationships

No Comments

No Known Activations