INDEX

Explanations

references to actions and their associated subjects or objects

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

"Got" or possessive words

np_acts-logits-general · gemini-2.0-flash

have/got followed by something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

mot

-0.27

ven

-0.26

Gu

-0.25

 kock

-0.25

 enregistrer

-0.25

use

-0.24

 Miss

-0.24

ala

-0.24

Processed

-0.24

gang

-0.23

POSITIVE LOGITS

 للمعارف

1.08

KommentareTeilen

1.04

parsedMessage

1.00

 surla

0.86

 ब्रेकडाउन

0.84

SourceChecksum

0.84

expandindo

0.84

sizeCache

0.83

 للاسماء

0.82

SequentialGroup

0.80

Activations Density 0.175%

references to actions and their associated subjects or objects

"Got" or possessive words

have/got followed by something

No Comments

No Known Activations