INDEX

Explanations

sections of text that contain programming or technical instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.86

 EClass

-0.66

Vidite

-0.58

Alike

-0.57

 Gans

-0.56

 betweenstory

-0.55

LookAnd

-0.54

AsUp

-0.54

 tartalomajánló

-0.54

protoimpl

-0.54

POSITIVE LOGITS

source

0.86

 source

0.64

 Inscrivez

0.63

—

0.61

Источник

0.59

bibfield

0.58

 IBOutlet

0.57

sou

0.57

 transfieras

0.57

مصادر

0.56

Activations Density 0.028%

sections of text that contain programming or technical instructions

No Comments

No Known Activations