INDEX

Explanations

references to speeches and addresses given by prominent figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 informasi

-0.47

ulam

-0.47

 fråga

-0.45

 informação

-0.44

tag

-0.43

 môn

-0.43

ullo

-0.43

 berge

-0.42

 Polri

-0.42

DialogFragment

-0.42

POSITIVE LOGITS

 Speeches

0.85

 speech

0.82

 speeches

0.81

tagext

0.79

complexContent

0.77

speech

0.76

makeConstraints

0.75

 Speech

0.75

 Paglinawan

0.72

Speech

0.70

Activations Density 0.195%

references to speeches and addresses given by prominent figures

No Comments

No Known Activations