INDEX

Explanations

references to specific items or concepts

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

sa

-0.46

 ponts

-0.45

Sa

-0.43

-0.42

Sa

-0.41

Tag

-0.41

 cima

-0.40

Tra

-0.39

cool

-0.39

POSITIVE LOGITS

----</

1.07

 ujednoznacz

1.04

脚注の使い方

1.02

rungsseite

0.96

 BoxFit

0.95

GOTREF

0.94

RegistryLite

0.91

GEBURTSDATUM

0.88

 NSCoder

0.86

__":

0.84

Activations Density 0.453%

references to specific items or concepts

No Comments

No Known Activations