INDEX

Explanations

phrases related to self-description or self-identification

oai_token-act-pair · gpt-3.5-turbo

the term "self-described" or "self-proclaimed" in relation to various identities or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

perature

-0.70

cos

-0.68

zes

-0.65

xes

-0.64

 ILCS

-0.62

ÃŃa

-0.62

oton

-0.62

Ö

-0.60

zers

-0.60

isons

-0.60

POSITIVE LOGITS

tarian

0.75

azeera

0.72

described

0.72

idable

0.69

unct

0.69

proclaimed

0.68

ream

0.68

 skept

0.67

\"

0.66

reprene

0.66

Activations Density 0.027%

phrases related to self-description or self-identification

the term "self-described" or "self-proclaimed" in relation to various identities or groups

No Comments

No Known Activations