INDEX

Explanations

terminology related to stages in processes or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

CrossRef

-0.88

riwal

-0.85

GRAFÍA

-0.81

]))

-0.81

}')

-0.81

 Vienne

-0.81

quoi

-0.80

ಿಸ

-0.78

 Lobo

-0.77

 Hül

-0.77

POSITIVE LOGITS

 Stage

1.76

 STAGE

1.73

Stage

1.68

STAGE

1.61

stage

1.60

 stage

1.55

 stages

1.48

stages

1.45

Stages

1.42

 Stages

1.40

Activations Density 0.025%

terminology related to stages in processes or classifications

No Comments

No Known Activations