INDEX

Explanations

code-related terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 متعلقه

-0.83

-0.82

 deſt

-0.80

tvguidetime

-0.77

 ſever

-0.76

ſelf

-0.76

 ſtill

-0.75

 tranſ

-0.74

 дописавши

-0.73

multirow

-0.72

POSITIVE LOGITS

 propOrder

0.65

GEBURTSDATUM

0.59

Autoritní

0.53

 bounce

0.44

 AssemblyCulture

0.41

 accedere

0.40

 catatan

0.38

 call

0.38

 RECEIVE

0.38

cal

0.37

Activations Density 0.999%

code-related terms and concepts

No Comments

No Known Activations