INDEX

Explanations

code structure expressions, specifically identifying return statements and control flow syntax

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

Code-related tokens and special characters

np_acts-logits-general · gemini-2.0-flash

equal to

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

int

-0.52

-0.50

uint

-0.48

his

-0.46

-0.45

ino

-0.45

–

-0.45

 annan

-0.45

-0.44

POSITIVE LOGITS

URLException

1.10

extAlignment

1.03

tagHelperRunner

0.96

 bezeichneter

0.96

__":

0.94

 Normdatei

0.91

astify

0.89

 وتسجيلات

0.89

ergies

0.89

 للاسماء

0.89

Activations Density 0.075%

code structure expressions, specifically identifying return statements and control flow syntax

Code-related tokens and special characters

equal to

No Comments

No Known Activations