INDEX

Explanations

references to API specifications and versions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

getItemId

-0.61

IsMutable

-0.56

niająca

-0.55

postsleuth

-0.54

خة

-0.54

=$((

-0.54

ogia

-0.53

@[+][

-0.51

hyrchwyd

-0.50

vaadin

-0.49

POSITIVE LOGITS

 APIs

0.66

 Varan

0.65

Cordialement

0.64

 ApiService

0.63

epy

0.63

 接口

0.63

ostante

0.63

 gräns

0.62

 keys

0.59

MethodImpl

0.59

Activations Density 0.037%

references to API specifications and versions

No Comments

No Known Activations