INDEX

Explanations

quoted names or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

нак

-0.66

様

-0.54

TagMode

-0.49

fan

-0.48

 виправивши

-0.48

IsString

-0.47

ikala

-0.47

 ligiloj

-0.47

||}

-0.46

 enlace

-0.46

POSITIVE LOGITS

Personendaten

0.77

 Chriftian

0.75

tvguidetime

0.75

 AttributeSet

0.73

 Majefty

0.72

Efq

0.69

حوالہ

0.69

 reaſon

0.67

 ſeveral

0.66

 himſelf

0.66

Activations Density 0.033%

quoted names or titles

No Comments

No Known Activations