INDEX

Explanations

the word "and" in various contexts

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

furter

-0.90

__':

-0.88

?,?,

-0.83

AutoField

-0.74

EndInit

-0.64

xffffff

-0.64

getMinutes

-0.61

 onOptions

-0.60

","");

-0.60

 AssemblyTitle

-0.59

POSITIVE LOGITS

 disambiguazione

0.68

gex

0.53

 оригіналу

0.52

 entram

0.51

chafts

0.48

 giustizia

0.48

GeneratedCode

0.47

tivitas

0.47

AddTagHelper

0.47

kosh

0.46

Activations Density 0.033%

the word "and" in various contexts

No Comments

No Known Activations

the word "and" in various contexts

No Comments

No Known Activations