INDEX

Explanations

phrases related to findings and results in a scientific or analytical context

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

 فريبيس

-0.90

IsMutable

-0.76

DockStyle

-0.72

InitVars

-0.71

Carriera

-0.69

 referenties

-0.66

})));

-0.64

piracy

-0.64

mpion

-0.63

lankton

-0.63

POSITIVE LOGITS

VersionUID

0.68

LogFactory

0.63

❋

0.54

AndroidJUnit

0.51

 DBNull

0.50

['$

0.48

 LIRE

0.47

 solito

0.46

 precisely

0.45

?,?,

0.44

Activations Density 0.023%

phrases related to findings and results in a scientific or analytical context

No Comments

No Known Activations