INDEX

Explanations

symbols and punctuation often found in programming or code structures

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

Code snippets with brackets/parentheses

np_acts-logits-general · gemini-2.0-flash

code structure syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

awtextra

-0.64

featureID

-0.59

GEBURTSDATUM

-0.55

setViewportView

-0.53

 kasarigan

-0.51

ervlak

-0.49

TagMode

-0.47

 AssemblyVersion

-0.47

Билгалдахарш

-0.45

mahl

-0.45

POSITIVE LOGITS

 forState

0.63

scalatest

0.45

 leider

0.41

 ayı

0.41

removeAttr

0.40

AnimationsModule

0.37

{}/

0.37

جستارهای

0.36

 ↓,

0.36

}[!

0.35

Activations Density 0.317%

symbols and punctuation often found in programming or code structures

Code snippets with brackets/parentheses

code structure syntax

No Comments

No Known Activations