INDEX

Explanations

unique identifiers or object names within a structured dataset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UnusedPrivate

-0.84

 OFDb

-0.71

出版年

-0.70

 nakalista

-0.63

 ſta

-0.62

 سكانية

-0.61

 houſe

-0.61

DeleteBehavior

-0.61

ésultats

-0.60

adaptiveStyles

-0.60

POSITIVE LOGITS

 Coyle

0.35

bk

0.34

0.33

 kasarigan

0.31

use

0.31

unistd

0.31

or

0.30

amb

0.30

range

0.30

Activations Density 0.337%

unique identifiers or object names within a structured dataset

No Comments

No Known Activations