INDEX

Explanations

numerical sequences and patterns within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 génie

-0.61

 démocratie

-0.57

EMPO

-0.57

 LIRE

-0.55

'],$

-0.55

 guerres

-0.54

 réactions

-0.54

Gdx

-0.54

 Dicapai

-0.53

 Glä

-0.53

POSITIVE LOGITS

RetentionPolicy

0.68

ViewFeatures

0.66

omitempty

0.63

SqlClient

0.60

+#+

0.60

RectangleBorder

0.60

tangentMode

0.58

OCCURRED

0.57

eff

0.57

 imageNamed

0.57

Activations Density 0.393%

numerical sequences and patterns within code

No Comments

No Known Activations