INDEX

Explanations

representations of the word "ignorance" or variations thereof

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "nig" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Franch

-0.67

 Sparkle

-0.63

 Emin

-0.60

 Sussex

-0.60

Ĥª

-0.57

ãĥ¢

-0.57

CSI

-0.57

 Leilan

-0.56

housing

-0.56

ÄŁ

-0.56

POSITIVE LOGITS

arette

1.28

gers

1.26

rams

1.18

arettes

1.18

glers

1.18

gered

1.14

lia

1.11

abyte

1.10

roups

1.09

raphic

1.08

Activations Density 0.060%

representations of the word "ignorance" or variations thereof

mentions of the term "nig" in various contexts

No Comments

No Known Activations