INDEX

Explanations

references to 'front' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 escolar

-0.88

MeasureSpec

-0.85

})*/

-0.83

 judiciaire

-0.77



-0.77

TintMode

-0.75

hysema

-0.74

 Archipelago

-0.74

 pédagogique

-0.73

 ecológico

-0.73

POSITIVE LOGITS

 front

3.00

 Front

2.74

front

2.72

Front

2.66

 FRONT

2.59

FRONT

2.37

 fronts

2.09

 fron

1.93

 Fron

1.80

fron

1.80

Activations Density 0.061%

references to 'front' in various contexts

No Comments

No Known Activations