INDEX

Explanations

specific programming-related terms and expressions regarding data handling and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

<bos>

-0.74

setVerticalGroup

-0.71

DockStyle

-0.69

 Gazetteer

-0.65

RetentionPolicy

-0.57

 BoxFit

-0.53

 חיצוניים

-0.53

 AssemblyVersion

-0.49

GenerationType

-0.48

SequentialGroup

-0.48

POSITIVE LOGITS

StoryboardSegue

0.65

횟

0.63

 censiti

0.60

 beverly

0.58

arean

0.58

 freg

0.57

 gawas

0.56

馳走

0.55

 marl

0.55

 Daß

0.54

Activations Density 0.330%

specific programming-related terms and expressions regarding data handling and manipulation

No Comments

No Known Activations