INDEX

Explanations

summaries and descriptive annotations related to classes and components in programming documentation

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

LookAnd

-0.61

enterOuterAlt

-0.54

プーン

-0.52

nt

-0.51

 Paglinawan

-0.50

 Leland

-0.48

 GetEnumerator

-0.47

ley

-0.45

est

-0.44

 suivez

-0.44

POSITIVE LOGITS

 الحره

1.35

RectangleBorder

1.06

summary

1.05

}")]

1.02

__":

1.01

__':

0.95

]));

0.95

migrationBuilder

0.95

)*/

0.94

0.92

Activations Density 0.007%

summaries and descriptive annotations related to classes and components in programming documentation

No Comments

No Known Activations