INDEX

Explanations

technical specifications and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

出版年

-0.67

 estekak

-0.67

 externi

-0.65

-0.62

rungsseite

-0.58

tagHelperRunner

-0.58

expandindo

-0.58

StoreMessageInfo

-0.58

MessageTagHelper

-0.57

 EconPapers

-0.55

POSITIVE LOGITS

 Réponses

0.63

principalTable

0.59

 lastly

0.56

 finally

0.56

TOTAL

0.55

finally

0.53

 Tutti

0.53

linspace

0.52

 infine

0.52

IMPORTED

0.50

Activations Density 0.497%

technical specifications and numerical data

No Comments

No Known Activations