INDEX

Explanations

repeated use of the word "at" in varying 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

 teş

-0.55

at

-0.51

Angleterre

-0.50

ofer

-0.48

pros

-0.48

 chez

-0.47

googleapis

-0.47

 Hause

-0.46

 espan

-0.46

Là

-0.46

POSITIVE LOGITS

 ModelExpression

0.93

SourceChecksum

0.81

AddTagHelper

0.81

 CURIAM

0.81

 nahilalakip

0.79

UnusedPrivate

0.76

 AssemblyVersion

0.75

 كومونز

0.71

 useAppContext

0.71

Geplaatst

0.70

Activations Density 0.063%

repeated use of the word "at" in varying contexts

No Comments

No Known Activations