INDEX

Explanations

phrases related to being true to something or someone

oai_token-act-pair · gpt-3.5-turbo

references to truthfulness and being true to oneself or others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

lain

-0.73

 hoops

-0.68

ioch

-0.66

 nets

-0.65

adelphia

-0.64

opens

-0.64

 Frazier

-0.63

 Regions

-0.63

zan

-0.63

ypes

-0.62

POSITIVE LOGITS

Jane

0.72

 believer

0.70

ãĤ·ãĥ£

0.66

dfx

0.66

DonaldTrump

0.65

verend

0.65

 Valkyrie

0.62

ACTED

0.62

mington

0.62

 Unlimited

0.60

Activations Density 0.084%

phrases related to being true to something or someone

references to truthfulness and being true to oneself or others

No Comments

No Known Activations