INDEX

Explanations

references to specific locations and mathematical expressions or equations

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

scientific names and math formulas

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

 nahilalakip

-0.60

tagHelperRunner

-0.54

AISSEE

-0.50

 Chwiliwch

-0.47

httphttps

-0.43

 noDo

-0.43

 мәкал

-0.42

tionalität

-0.41

 Wikimedijinoj

-0.40

optionalTypeArgs

-0.40

POSITIVE LOGITS

GenerationType

0.49

avut

0.48

astify

0.46



0.45

LabelTagHelper

0.45

CloseOperation

0.44

請繼續往下閱讀

0.44

cshtml

0.43

IUrlHelper

0.43

ResumeLayout

0.43

Activations Density 0.054%

references to specific locations and mathematical expressions or equations

scientific names and math formulas

No Comments

No Known Activations