INDEX

Explanations

references to specific individuals or names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 AssemblyCulture

-0.76

tagHelperRunner

-0.65

addPreferredGap

-0.64

‍♂️

-0.64

 propOrder

-0.61

 للاسماء

-0.60

KURZBESCHREIBUNG

-0.59

ViewImports

-0.59

 وتسجيلات

-0.58

تقاوى

-0.58

POSITIVE LOGITS

abelle

0.64

marie

0.58

ina

0.56

lyn

0.56

elyn

0.55

 businesswoman

0.55

wenn

0.54

Ann

0.54

leen

0.53

ilyn

0.52

Activations Density 0.177%

references to specific individuals or names

No Comments

No Known Activations