INDEX

Explanations

references to workshops and PR (public relations) related content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 estadísticas

-0.52

 createState

-0.47

 escudo

-0.44

ⓧ

-0.44

ництва

-0.43

 statistics

-0.43

 fichas

-0.43

 Conferencia

-0.43

 flotante

-0.42

 plazos

-0.42

POSITIVE LOGITS

fit

0.81

 workshops

0.74

PR

0.73

Fit

0.73

PR

0.72

Fit

0.71

 Workshops

0.69

 Workshop

0.69

FIT

0.69

 workshop

0.65

Activations Density 0.117%

references to workshops and PR (public relations) related content

No Comments

No Known Activations