INDEX

Explanations

references to authors and their contributions in academic and scientific texts

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

authors with surnames starting with B

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

DockStyle

-0.74

 <<<<<<<<<<<<<<

-0.65

ագրություններ

-0.64

twimg

-0.62

nodoc

-0.59

IntoConstraints

-0.57

 GenerationType

-0.57

StructEnd

-0.56

IndentedString

-0.55

ValueStyle

-0.55

POSITIVE LOGITS

期刊论文

0.30

暂无

0.30

了呢

0.30

Tikang

0.26

 European

0.26

 fré

0.26

 полі

0.25

 asist

0.25

 deca

0.25

 Participating

0.24

Activations Density 0.289%

references to authors and their contributions in academic and scientific texts

authors with surnames starting with B

No Comments

No Known Activations