INDEX

Explanations

sections of text with no significant content or activations

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

Punctuation and symbols

np_acts-logits-general · gemini-2.0-flash

words after "of"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

fhir

-0.63

 Florence

-0.46

 tableName

-0.45

atta

-0.44

 Orrell

-0.44

Ing

-0.43

astéroïdes

-0.42

vably

-0.42

ฟ้า

-0.42

bè

-0.42

POSITIVE LOGITS

adaptiveStyles

0.94

tvguidetime

0.78

ScopeManager

0.78

GEBURTSDATUM

0.70

WriteTagHelper

0.69

 متعلقه

0.65

 dieux

0.64

DotNetBar

0.62

StoryboardSegue

0.61

 transfieras

0.60

Activations Density 0.023%

sections of text with no significant content or activations

Punctuation and symbols

words after "of"

No Comments

No Known Activations