INDEX

Explanations

contractions and possessives, particularly related to negation and ownership

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.79

 intersper

-2.29

 hairc

-1.90

 hentai

-1.87

 milf

-1.81

 swarovski

-1.73

 encomp

-1.73

 snoopy

-1.73

 inconce

-1.71

 impra

-1.69

POSITIVE LOGITS

 optik

0.88

 demokra

0.83

 kalori

0.81

 seksi

0.78

’

0.77

mathrm

0.77

 terci

0.76

 keramik

0.75

 elektronik

0.74

 Meksiko

0.73

Activations Density 0.414%

contractions and possessives, particularly related to negation and ownership

No Comments

No Known Activations