INDEX

Explanations

programming-related syntax and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fillType

-0.66

yym

-0.59

AccessorTable

-0.57

ScopeManager

-0.55

 Autorizaciones

-0.54

 defaultstate

-0.54

TagMode

-0.52

piram

-0.52

 Signalez

-0.52

providedIn

-0.52

POSITIVE LOGITS

Clr

0.70

ClientRect

0.45

 uved

0.41

 föruts

0.36

appcompat

0.35

 hôte

0.35

 précédentes

0.34

receiving

0.34

 previously

0.34

此前

0.33

Activations Density 0.002%

programming-related syntax and identifiers

No Comments

No Known Activations