INDEX

Explanations

demonstrative pronouns indicating proximity or reference to specific things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 initComponents

-0.57

 following

-0.54

 below

-0.53

ttemberg

-0.51

 jLabel

-0.51

lenburg

-0.50

 foon

-0.50

inephrine

-0.50

Efq

-0.50

berdayakan

-0.48

POSITIVE LOGITS

QMetaType

0.78

XmlType

0.68

ChildIndex

0.67

matchCondition

0.66

ValueStyle

0.65

TypedDataSet

0.63

StoryboardSegue

0.62

webElementGuid

0.61

வ்

0.59

τσι

0.59

Activations Density 0.172%

demonstrative pronouns indicating proximity or reference to specific things

No Comments

No Known Activations