INDEX

Explanations

patterns or sequences within structured data or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

SourceChecksum

-0.75

 ***!

-0.74

RTLD

-0.68

 <<<<<<<<<<<<<<

-0.64

hyrchwyd

-0.63

Begriffsklä

-0.59

 AspNetCore

-0.58

 урна

-0.57

MarshalTo

-0.56

 bezeichneter

-0.56

POSITIVE LOGITS

Hay

0.50

 regency

0.47

(?)

0.46

enumi

0.46

Hay

0.46

 fays

0.45

 noten

0.45

Referencies

0.45

**/

0.44

Referencias

0.44

Activations Density 0.131%

patterns or sequences within structured data or identifiers

No Comments

No Known Activations