INDEX

Explanations

specific variable assignments within code snippets

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

instantiation of objects

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

/***/

-0.43

ɵɵelementEnd

-0.40

۪

-0.40

 quota

-0.40

 permanence

-0.38

endpush

-0.36

Gön

-0.36

adding

-0.35

地

-0.34

✤

-0.34

POSITIVE LOGITS

RegressionTest

0.64

 informée

0.60

pecabe

0.59

setVerticalGroup

0.56

OCCURRED

0.56

httphttps

0.56

 мәкал

0.54

haikusbot

0.54

principalColumn

0.54

 للاسماء

0.54

Activations Density 0.015%

specific variable assignments within code snippets

instantiation of objects

No Comments

No Known Activations