INDEX

Explanations

abbreviations or acronyms commonly found in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-0.79

-0.70

 Italijanski

-0.60

-0.58

AAT

-0.58

openSession

-0.56

Geografia

-0.55

awakeFromNib

-0.55

AAS

-0.55

OTO

-0.54

POSITIVE LOGITS

0.59

fastjson

0.52

0.51

0.50

Ts

0.49

 bientôt

0.49

Personendaten

0.48

ся

0.48

뀔

0.47

WebElementEntity

0.44

Activations Density 0.649%

abbreviations or acronyms commonly found in scientific or technical contexts

No Comments

No Known Activations