INDEX

Explanations

references to games

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

تقاوى

-0.65

 unknownFields

-0.61

 INCLUD

-0.59

 riuscito

-0.59

unknownFields

-0.58

onOptions

-0.57

 prière

-0.56

Manbalar

-0.55

 upholstered

-0.55

Immer

-0.54

POSITIVE LOGITS

 contra

1.07

 Game

0.87

し

0.77

 contrary

0.71

openhague

0.70

wertig

0.70

 Contra

0.69

ukone

0.69

 typelib

0.65

contra

0.64

Activations Density 0.067%

references to games

No Comments

No Known Activations