INDEX

Explanations

phrases and structures that indicate additional information or supplementary content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ıdır

-0.59

emptory

-0.58

 Monfieur

-0.55

 absolutely

-0.54

astéroïdes

-0.53

 writ

-0.52

 Instantiate

-0.52

 removeFrom

-0.52

 mAdapter

-0.52

 Played

-0.51

POSITIVE LOGITS

LookAnd

0.70

他に

0.68

кож

0.62

 doInBackground

0.60

tdessen

0.55

SuspendLayout

0.54

rungsseite

0.53

AndEndTag

0.51

代わりに

0.51

ioutil

0.51

Activations Density 0.235%

phrases and structures that indicate additional information or supplementary content

No Comments

No Known Activations