INDEX

Explanations

code-related terms and structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BASEPATH

-0.80

 AssemblyTitle

-0.72

AsUp

-0.69

олові

-0.69

requireNonNull

-0.64

IntentFilter

-0.63

 Allociné

-0.62

Filmografie

-0.61

IVEREF

-0.61

providedIn

-0.61

POSITIVE LOGITS

 sprig

0.53

 tundra

0.51

 corne

0.49

 cruc

0.49

 whoſe

0.49

 espin

0.48

 orphanage

0.48

 Lynx

0.48

Autoritní

0.47

 Mortar

0.46

Activations Density 1.972%

code-related terms and structures

No Comments

No Known Activations