INDEX

Explanations

references to visual indicators and lines in diagrams or charts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

↹

-0.53

Cartney

-0.52

듦

-0.51

 Hague

-0.50

NameInMap

-0.49

Попис

-0.48

 rafts

-0.48

vale

-0.47

fourths

-0.47

aughters

-0.46

POSITIVE LOGITS

 виправивши

0.49

 ContentValues

0.48

enumi

0.42

 AssemblyVersion

0.41

DockStyle

0.39



0.39

########.

0.36

 presidencia

0.36

ViewImports

0.36

참고

0.35

Activations Density 0.955%

references to visual indicators and lines in diagrams or charts

No Comments

No Known Activations