INDEX

Explanations

instances of the word "that" in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

íč

-0.50

ympto

-0.50

Portale

-0.50

 المقبل

-0.50

sdag

-0.49

 miliardi

-0.48

 prieš

-0.48

κλη

-0.48

Rela

-0.48

 prochain

-0.48

POSITIVE LOGITS

findpost

0.73

 kasarigan

0.69

intahan

0.65

 Infatti

0.64

 ThemeData

0.63

 Vikipedi

0.59

tagHelperRunner

0.57

AntiForgeryToken

0.56

 bowiem

0.56

 mergeFrom

0.55

Activations Density 0.193%

instances of the word "that" in varying contexts

No Comments

No Known Activations

instances of the word "that" in varying contexts

No Comments

No Known Activations