INDEX

Explanations

occurrences of wildcard or special character notations in code or documentation

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

SQL count(*) queries

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

 EconPapers

-0.57

 незавершена

-0.53

 AssemblyVersion

-0.50

 saites

-0.47

OCCURRED

-0.47

 configurer

-0.46

ENOS

-0.46

Enlaces

-0.46

 propTypes

-0.46

Спољашње

-0.45

POSITIVE LOGITS

'*'

0.95

"*"

0.55

 '*':

0.53

 '*',

0.52

 '*')

0.50

'+'

0.43

__((

0.42

('*',

0.42

 ParseException

0.40

 "*",

0.40

Activations Density 0.002%

occurrences of wildcard or special character notations in code or documentation

SQL count(*) queries

No Comments

No Known Activations