INDEX

Explanations

mentions of different stages or phases in a process or treatment

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

riwal

-0.82

GRAFÍA

-0.74

 Bruxelles

-0.70

<0xD4>

-0.67

спользова

-0.67

 estri

-0.65

]--;

-0.65

?>

-0.65

fik

-0.63

mith

-0.63

POSITIVE LOGITS

 STAGE

1.53

 Stage

1.48

Stage

1.46

STAGE

1.39

stage

1.35

 stage

1.33

 PHASE

1.28

 stages

1.26

 Stages

1.25

Stages

1.25

Activations Density 0.052%

mentions of different stages or phases in a process or treatment

No Comments

No Known Activations