INDEX

Explanations

words related to contributions or inputs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

évaluateur

-0.84

 insuffisamment

-0.82

Хьажоргаш

-0.78

putan

-0.75

ScopeManager

-0.75

 disambiguazione

-0.74

COA

-0.66

WithIOException

-0.65

complexContent

-0.65

enity

-0.64

POSITIVE LOGITS

 significant

0.94

significant

0.91

Significant

0.88

 Significant

0.86

 SIGNIFIC

0.77

 contributing

0.76

 significativos

0.74

 significantly

0.73

 significativo

0.72

 contribué

0.71

Activations Density 0.125%

words related to contributions or inputs

No Comments

No Known Activations