INDEX

Explanations

technical terms and jargon related to devices and electrical components

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

before commas or clauses

np_acts-logits-general · gemini-2.0-flash

geographical locations and specific entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

contentLoaded

-0.90

帖最后由

-0.85

UnusedPrivate

-0.84

 Савезне

-0.76

^(@)

-0.76

ConstraintMaker

-0.75

 Exactos

-0.73

$_"

-0.73

posedge

-0.72

 دیکھیے

-0.72

POSITIVE LOGITS

SPATH

0.55

把

0.51

 redis

0.50

re

0.50

put

0.49

 attempted

0.46

 systematically

0.45

 entrust

0.44

 retra

0.44

Enders

0.42

Activations Density 1.419%

technical terms and jargon related to devices and electrical components

before commas or clauses

geographical locations and specific entities

No Comments

No Known Activations