INDEX

Explanations

technical terms related to optimization and statistical measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

WebServlet

-0.58

hoeddwyd

-0.53

Referencies

-0.52

xtick

-0.52

},[])

-0.52

########.

-0.51

حياته

-0.51

DebuggerNonUser

-0.50

saraba

-0.49

حياتها

-0.49

POSITIVE LOGITS

 cost

0.82

 objective

0.82

 loss

0.78

Objective

0.75

objective

0.74

cost

0.72

 minimization

0.71

 minimized

0.71

 Loss

0.69

 metric

0.68

Activations Density 1.631%

technical terms related to optimization and statistical measurements

No Comments

No Known Activations