INDEX

Explanations

references to research articles and academic citations

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

 AssemblyVersion

-0.67

ViewImports

-0.62

InstanceState

-0.54

rungsseite

-0.53

قایناق‌لار

-0.53

BeginContext

-0.52

 sonora

-0.51

 valable

-0.51

vece

-0.51

 Ingenie

-0.50

POSITIVE LOGITS

Suppl

0.89

 Suppl

0.88

pii

0.71

 PMID

0.69

 supp

0.65

PMID

0.64

rimir

0.64

doi

0.63

 PubMed

0.63

PubMed

0.62

Activations Density 0.337%

references to research articles and academic citations

No Comments

No Known Activations