INDEX

Explanations

occurrences of code elements or syntax

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

<start_of_turn> user

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

transQ

-0.62

 betweenstory

-0.58

 يتيمه

-0.57

OGND

-0.54

RectangleBorder

-0.53

ThroughAttribute

-0.52

+#+#

-0.52

RegressionTest

-0.48

medriver

-0.47

onViewCreated

-0.47

POSITIVE LOGITS

GenerationType

0.48

RequestMethod

0.39

 thinking

0.39

Hentet

0.37

 affez

0.37

rbrakk

0.36

quema

0.36

getTag

0.36

 Tight

0.36

 AssemblyVersion

0.35

Activations Density 0.000%

occurrences of code elements or syntax

<start_of_turn> user

No Comments

No Known Activations

occurrences of code elements or syntax

<start_of_turn> user

No Comments

No Known Activations