INDEX

Explanations

parentheses and related syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

-0.59

qua

-0.54

so

-0.52

-0.50

cap

-0.50

tri

-0.49

阑

-0.49

Per

-0.48

Ro

-0.48

WritableDatabase

-0.48

POSITIVE LOGITS

Diweddarwch

0.97

tvguidetime

0.92

Personensuche

0.86

 kasarigan

0.79

PerformLayout

0.76

SequentialGroup

0.75

 незавершена

0.73

adaptiveStyles

0.73

 Whigs

0.73

EndProject

0.72

Activations Density 0.041%

parentheses and related syntax

No Comments

No Known Activations