INDEX

Explanations

terms and concepts related to search and filtering functionalities in programming

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

search and filter

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

 agon

-0.47

 agonizing

-0.40

 ControllerBase

-0.40

ENES

-0.37

 agony

-0.37

 Rame

-0.37

 Will

-0.36

intă

-0.36

ES

-0.35

 Analysts

-0.35

POSITIVE LOGITS

ChildScrollView

0.73

unknownFields

0.62

aarrggbb

0.55

EDEFAULT

0.54

RectangleBorder

0.52

 NSCoder

0.52

enderror

0.51

 समीक्षाओं

0.49

#+#

0.49

ActionCreators

0.48

Activations Density 0.004%

terms and concepts related to search and filtering functionalities in programming

search and filter

No Comments

No Known Activations