INDEX

Explanations

programming-related terminology and syntax elements

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

Code, imports, or package names

np_acts-logits-general · gemini-2.0-flash

start of turn text

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 betweenstory

-0.43

 Numerade

-0.43

 Offisielt

-0.38

UnusedPrivate

-0.36

Gambas

-0.35

omotor

-0.34

 sark

-0.34

 invokingState

-0.33

Tap

-0.33

ddha

-0.33

POSITIVE LOGITS

 propOrder

0.60

isContained

0.59

contentLoaded

0.52

 autorytatywna

0.50

OGND

0.49

:+:

0.49

 للمعارف

0.48

AutoScaleMode

0.46

########.

0.45

 kasarigan

0.44

Activations Density 0.095%

programming-related terminology and syntax elements

Code, imports, or package names

start of turn text

No Comments

No Known Activations