INDEX

Explanations

function calls

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

 houſe

-0.52

iconque

-0.46

iertamente

-0.43

 pleaſure

-0.43

 peines

-0.41

 Houſe

-0.41

ArgumentParser

-0.40

Slf

-0.39

drawSprites

-0.38

 ſte

-0.38

POSITIVE LOGITS

__*/

0.50

̈́

0.47

帖最后由

0.47

createCanvas

0.46

cupa

0.46

rabi

0.46



0.45

 doInBackground

0.45

()%

0.44

Activations Density 0.002%

function calls

<start_of_turn> user

No Comments

No Known Activations

function calls

<start_of_turn> user

No Comments

No Known Activations