INDEX

Explanations

phrases related to societal or cultural observations and critiques

oai_token-act-pair · gpt-3.5-turbo

references to new trends or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ŃĶ

-0.80

xtap

-0.76

cffffcc

-0.72

cheon

-0.70

é¾įåĸļå£«

-0.68

 negotiator

-0.68

 deft

-0.67

 maneu

-0.64

chief

-0.63

ATHER

-0.63

POSITIVE LOGITS

 banning

0.84

 pedoph

0.79

 paed

0.77

 homosexuality

0.77

 monog

0.76

 virginity

0.76

gay

0.76

 bans

0.76

 homosexuals

0.74

 banned

0.74

Activations Density 0.697%

phrases related to societal or cultural observations and critiques

references to new trends or concepts

No Comments

No Known Activations