INDEX

Explanations

numeric values and their contextual implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

Personendaten

-0.85

 تضيفلها

-0.77

 typelib

-0.77

featureID

-0.71

:✨

-0.70

 protoimpl

-0.69

 difficiles

-0.65

 resourceCulture

-0.65

Personensuche

-0.63

ISupport

-0.61

POSITIVE LOGITS

ervant

0.63

oughly

0.62

 ElementRef

0.61

 समीक्षाओं

0.57

levance

0.57

versy

0.57

ädie

0.55

rungsseite

0.55

 roland

0.55

psons

0.54

Activations Density 0.193%

numeric values and their contextual implications

No Comments

No Known Activations