INDEX

Explanations

mathematical symbols and formatting used in equations

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

cal L

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

 estekak

-0.69

Архівовано

-0.62

 ErrIntOverflow

-0.48

曖昧さ回避

-0.46

 HasFactory

-0.45

 AssemblyProduct

-0.42

 Lengkap

-0.42

MemoryWarning

-0.41

 ролях

-0.41

 siècles

-0.40

POSITIVE LOGITS

"}")

0.54

("")]

0.52

WriteTagHelper

0.50

Rhestr

0.46

/¯

0.46

<()>

0.46

瑙

0.46

ioutil

0.45

 trauma

0.45

uxxxx

0.44

Activations Density 0.506%

mathematical symbols and formatting used in equations

cal L

No Comments

No Known Activations