INDEX

Explanations

declarations of variables using the "let" keyword

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 متعلقه

-0.78

 odkazy

-0.74

 وتسجيلات

-0.73

xial

-0.72

IGraphics

-0.68

 InputDecoration

-0.66

__*/

-0.66

Erreferentziak

-0.66

 برانيه

-0.66

apnews

-0.64

POSITIVE LOGITS

BeginContext

0.73

synthesize

0.60

chequer

0.59

konos

0.56

VAR

0.53

 Pila

0.49

іга

0.48

EditText

0.48

Tet

0.48

BindingSource

0.48

Activations Density 0.027%

declarations of variables using the "let" keyword

No Comments

No Known Activations