INDEX

Explanations

terms and references related to scientific and technical concepts

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

preceding technical or numerical terms

np_acts-logits-general · gemini-2.0-flash

specific quantities or types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 المعيارى

-0.72

featureID

-0.71

 виправивши

-0.69

 nakalista

-0.68

 Geiſt

-0.67

 indígen

-0.66

 increí

-0.65

 Verſ

-0.65

[@BOS@]

-0.64

<unused32>

-0.64

POSITIVE LOGITS

 whose

0.33

 family

0.31

 that

0.30

ClientRect

0.28

าล

0.28

 equivalent

0.28

 residing

0.28

 henvisninger

0.28

Activations Density 0.922%

terms and references related to scientific and technical concepts

preceding technical or numerical terms

specific quantities or types

No Comments

No Known Activations