INDEX

Explanations

repeated phrases or constructions that include the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 uſe

-0.58

NFA

-0.58

Efq

-0.56

SLP

-0.56

ıntı

-0.56

 vierge

-0.55

 רבה

-0.55

 autorité

-0.55

ADI

-0.55

 fhew

-0.54

POSITIVE LOGITS

 дописавши

0.84

 nahilalakip

0.83

 Wikimedijinoj

0.81

irical

0.81

Hentet

0.81

cyklopedia

0.80

GEBURTSDATUM

0.78

ême

0.78

/**

0.74

исленность

0.74

Activations Density 0.063%

repeated phrases or constructions that include the word "of."

No Comments

No Known Activations