INDEX

Explanations

code snippets or syntax elements related to functions and their definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Hickey

-0.68

ו

-0.61

 Stubbs

-0.59

ה

-0.58

 Joseph

-0.58

 Cleo

-0.57

 Wadsworth

-0.57

-0.56

 Abbe

-0.56

 baroque

-0.56

POSITIVE LOGITS

."</

1.07

 незавершена

0.95

setVerticalGroup

0.94

'])){

0.92

)++;

0.91

 становника

0.89

).</

0.89

Personensuche

0.86

 الحره

0.85

++){

0.85

Activations Density 0.312%

code snippets or syntax elements related to functions and their definitions

No Comments

No Known Activations