INDEX

Explanations

tokens that indicate special commands or configuration settings in a programming context

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

commands and code snippets

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

 iconTwitter

-0.37

istoitu

-0.37

цездатний

-0.36

 оригіналу

-0.34

 istrinya

-0.33

hoeddwyd

-0.32

___]

-0.32

حوالہ

-0.32

"):

-0.31

Jereo

-0.31

POSITIVE LOGITS

ophenol

0.55

 FetchType

0.54

qtype

0.52

Resolution

0.52

 Resolution

0.50

naio

0.50

zey

0.50

boy

0.50

Brainz

0.50

zionalità

0.49

Activations Density 0.034%

tokens that indicate special commands or configuration settings in a programming context

commands and code snippets

No Comments

No Known Activations