INDEX

Explanations

references to scientific publications and documents

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

start of user turn

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

ReusableCell

-0.63

neux

-0.57

LabelTagHelper

-0.56

Gön

-0.55

MemoryWarning

-0.51

 חיצוניים

-0.50

interopRequire

-0.50

 surla

-0.50

 متعلقه

-0.50

NgModule

-0.50

POSITIVE LOGITS

 ConstraintSet

0.34

 jScrollPane

0.32

Easy

0.31

 online

0.31

Спасылкі

0.31

Ac

0.30

الدراسه

0.29

 register

0.29

ISD

0.29

系

0.29

Activations Density 0.000%

references to scientific publications and documents

start of user turn

No Comments

No Known Activations