INDEX

Explanations

numeric values indicating measurements or quantities

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

webElement

-0.62

fjspx

-0.61

transQ

-0.56

WebElementEntity

-0.51

AndEndTag

-0.48

WriteTagHelper

-0.48

-0.45

hoeddwyd

-0.44

Unmanaged

-0.44

wikimedia

-0.43

POSITIVE LOGITS

EDEFAULT

0.76

PreExecute

0.66

quelize

0.62

NUMX

0.61

AndroidJUnit

0.61

didReceive

0.61

GRAPHS

0.60

帖最后由

0.58

 Toen

0.57

Kaynakça

0.57

Activations Density 0.619%

numeric values indicating measurements or quantities

No Comments

No Known Activations