INDEX

Explanations

personal identifiers and roles within the context of relationships or experiences

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

ligare

-0.64

 Pronto

-0.59

rency

-0.57

 fallo

-0.55

 truc

-0.54

 micro

-0.54

hastly

-0.54

miyor

-0.54

pue

-0.53

micro

-0.53

POSITIVE LOGITS

AndEndTag

0.77



0.69

身为

0.67

 oprot

0.63

 resourceCulture

0.60

__*/

0.56

 autorytatywna

0.55

Дереккөздер

0.55

脚注の使い方

0.55

 дописавши

0.54

Activations Density 0.174%

personal identifiers and roles within the context of relationships or experiences

No Comments

No Known Activations