INDEX

Explanations

references to elements in programming, specifically in contexts related to selection and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

-0.51

who

-0.43

 Downey

-0.41

 Bischof

-0.40

How

-0.40

 hiking

-0.40

 organised

-0.39

stdio

-0.39

POSITIVE LOGITS

ElementException

0.95

 ElementRef

0.93

SBATCH

0.77

Element

0.76

ReusableCell

0.75

theless

0.74

 Geiſt

0.71

PerformLayout

0.71

 Element

0.69

 miniaturka

0.68

Activations Density 0.191%

references to elements in programming, specifically in contexts related to selection and manipulation

No Comments

No Known Activations