INDEX

Explanations

references to academic works or citations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lugar

-0.57

 Halls

-0.55

 géographie

-0.54

 говоря

-0.51

onians

-0.47

 studenti

-0.47

言えば

-0.47

 Ministério

-0.47

statements

-0.47

-0.46

POSITIVE LOGITS

 فريبيس

0.84

ьаж

0.77

expandindo

0.66

脚注の使い方

0.65

twimg

0.63

 disambiguazione

0.63

KURZBESCHREIBUNG

0.58

styleType

0.58

醐

0.56

 Affiliations

0.56

Activations Density 0.224%

references to academic works or citations

No Comments

No Known Activations