INDEX

Explanations

references to character names or identifiers within narrative 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

UnknownFieldSet

-0.57

To

-0.56

To

-0.48

webElementXpaths

-0.48

slidesToShow

-0.47

-0.46

ënten

-0.45

vensko

-0.44

 braccio

-0.44

per

-0.44

POSITIVE LOGITS

őben

0.88

ంలో

0.81

 Мексичка

0.79

 snippetHide

0.78

uksessa

0.76

országban

0.76

 में

0.75

ksessa

0.75

 Normdatei

0.74

ⓧ

0.74

Activations Density 1.606%

references to character names or identifiers within narrative contexts

No Comments

No Known Activations