INDEX

Explanations

references to coding concepts and structures, specifically within object-oriented programming and dependency injection frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

########.

-0.74

CodeAttribute

-0.72

SerializedName

-0.68

PerformLayout

-0.67

esgue

-0.67

AccessFile

-0.62

 дописавши

-0.61

 nakalista

-0.60

extAlignment

-0.59

Affirmed

-0.58

POSITIVE LOGITS

 injection

0.95

 inject

0.92

 Injection

0.88

 injected

0.88

DI

0.84

 injections

0.84

 injecting

0.82

 injector

0.80

inject

0.78

 Inject

0.77

Activations Density 0.274%

references to coding concepts and structures, specifically within object-oriented programming and dependency injection frameworks

No Comments

No Known Activations