INDEX

Explanations

actions related to saving, extracting data, and making selections or determinations in data structures or processes

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

technical terms and actions

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

IntoConstraints

-0.63

 Walkover

-0.57

最快更新

-0.56

/**

-0.56

Viited

-0.54

Ral

-0.53

onomía

-0.53

Whi

-0.52

 Discussion

-0.52

 Affiliations

-0.52

POSITIVE LOGITS

WithIOException

0.41

findpost

0.40

antası

0.37

 noDo

0.36

Kaieteur

0.31

cuado

0.30

 zanah

0.29

 Matériau

0.29

atimes

0.29

TagMode

0.28

Activations Density 0.089%

actions related to saving, extracting data, and making selections or determinations in data structures or processes

technical terms and actions

No Comments

No Known Activations