INDEX

Explanations

references to the front part of objects or entities

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

MeasureSpec

-0.96

 escolar

-0.90

 poussière

-0.88

 culturelles

-0.85

ukone

-0.84

TintMode

-0.83

styrelsen

-0.80

 religieuses

-0.79

 judiciaire

-0.79

 vaisselle

-0.79

POSITIVE LOGITS

 front

1.62

 Front

1.52

 FRONT

1.51

front

1.48

Front

1.44

FRONT

1.33

 fron

1.18

Fron

1.15

 fronts

1.15

 Fron

1.13

Activations Density 0.045%

references to the front part of objects or entities

No Comments

No Known Activations