INDEX

Explanations

significant numerical values and identifiers within a structured format

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

Code and special characters

np_acts-logits-general · gemini-2.0-flash

function definitions and code structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ukone

-0.61

XtraEditors

-0.58

setVerticalGroup

-0.53

kloped

-0.53

envolvimento

-0.52

wende

-0.52

DebuggerNonUser

-0.50

gouv

-0.50

ləş

-0.50

 onItemClick

-0.50

POSITIVE LOGITS

发表于

0.50

einander

0.47

 respeito

0.47

ครัว

0.44

}\]

0.44

)‏

0.44

 preocupes

0.43

">+

0.43

 Absent

0.43

 Signalez

0.43

Activations Density 0.265%

significant numerical values and identifiers within a structured format

Code and special characters

function definitions and code structures

No Comments

No Known Activations