INDEX

Explanations

key technical terms and specific data points in a scientific context

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

technical terms and their properties

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

setContentView

-0.44

extAlignment

-0.39

mány

-0.39

sizeCache

-0.37

StoryboardSegue

-0.37

errHandler

-0.37

 MessageBoxIcon

-0.37

RepeatedField

-0.36

itemBuilder

-0.36

Binder

-0.35

POSITIVE LOGITS

PreferredItem

0.51

principalColumn

0.45

 propOrder

0.44

HasIndex

0.44

Microkernel

0.42

itespace

0.42

 ajustar

0.41

styleType

0.40

Grüsse

0.40

rungsseite

0.39

Activations Density 0.177%

key technical terms and specific data points in a scientific context

technical terms and their properties

No Comments

No Known Activations