INDEX

Explanations

technical terminology and actions related to systems and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

can

-0.48

<eos>

-0.46

greenrobot

-0.43

 pote

-0.43

 could

-0.42

 bien

-0.42

Filed

-0.41

 passat

-0.41

 particular

-0.40

or

-0.40

POSITIVE LOGITS

حياتها

0.85

StoryboardSegue

0.82

 meste

0.80

 Anſ

0.79

KURZBESCHREIBUNG

0.76

 relève

0.73

 Unmarshal

0.72

 المعيارى

0.72

 Wikimedijinoj

0.72

 décid

0.72

Activations Density 0.488%

technical terminology and actions related to systems and processes

No Comments

No Known Activations