INDEX

Explanations

patterns and formatting in data or code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

findpost

-0.66

 demografica

-0.51

fromCharCode

-0.49

 betweenstory

-0.43

 adipis

-0.42

Gambas

-0.40

كويكب

-0.39

Makefile

-0.39

 chì

-0.39

matism

-0.39

POSITIVE LOGITS

IntoConstraints

0.65

 JpaRepository

0.64

AGB

0.62

 Theſe

0.61

 Tuli

0.61

 tribune

0.61

 asiatique

0.60

AddField

0.59

帖最后由

0.58

ChildScrollView

0.58

Activations Density 0.305%

patterns and formatting in data or code snippets

No Comments

No Known Activations