INDEX

Explanations

code comments and metadata related to modules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

netbeans

-0.63

 onAnimation

-0.62

 Shakspeare

-0.61

TargetException

-0.58

wußt

-0.56

UnitTesting

-0.55

MOQ

-0.53

олові

-0.53

ollectionView

-0.53

reactstrap

-0.51

POSITIVE LOGITS

filepath

0.74

tvguidetime

0.67

[*]

0.62

 filepath

0.60

expandindo

0.60

oprecip

0.59

 виправивши

0.59

 tartalomajánló

0.59

principalTable

0.58

 Rapids

0.57

Activations Density 0.074%

code comments and metadata related to modules

No Comments

No Known Activations