INDEX

Explanations

references to specific elements or concepts, particularly those indicated by 'this' or 'these'

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

ฤ

-0.46

 biti

-0.45

riente

-0.44

 sula

-0.44

ratto

-0.43

Shortest

-0.43

 apparti

-0.42

conducting

-0.42

 chefe

-0.42

öz

-0.42

POSITIVE LOGITS

 ujednoznacz

0.86

tvguidetime

0.79

脚注の使い方

0.79

 Dadurch

0.78

 solche

0.74

!*\

0.71

Cela

0.71

>>()

0.71

 latter

0.70

 Esto

0.69

Activations Density 0.586%

references to specific elements or concepts, particularly those indicated by 'this' or 'these'

No Comments

No Known Activations