INDEX

Explanations

references to terms and conditions regarding usage and distribution of software or data

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

user prompts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 smug

-0.33

 pumping

-0.31

 break

-0.31

Subviews

-0.30

pon

-0.30

stackrel

-0.30

 poured

-0.30

 board

-0.30

mon

-0.29

 pumped

-0.29

POSITIVE LOGITS

 للمعارف

0.76

ScopeManager

0.66

httphttps

0.65

 صوتيه

0.64

ChildScrollView

0.63

mybatisplus

0.61

setVerticalGroup

0.60

 geſch

0.60

 ModelExpression

0.60

 AssemblyTitle

0.59

Activations Density 0.004%

references to terms and conditions regarding usage and distribution of software or data

user prompts

No Comments

No Known Activations