INDEX

Explanations

references to documentation or related technical materials

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

-0.75

car

-0.75

 Dyer

-0.72

ewel

-0.71

es

-0.71

tom

-0.70

 mill

-0.70

 Muir

-0.69

providedIn

-0.69

:✨

-0.69

POSITIVE LOGITS

bibinfo

0.81

izophrenia

0.78

rungsseite

0.76

toJSON

0.76

 '\\;'

0.75

veillance

0.74

vily

0.74

addData

0.74

']")

0.74

Семья

0.73

Activations Density 0.199%

references to documentation or related technical materials

No Comments

No Known Activations