INDEX

Explanations

references to specific software components 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 @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

UnusedPrivate

-0.61

☸

-0.54

WebVitals

-0.51

ล้ว

-0.48

AnimationsModule

-0.48

rawtypes

-0.47

 تكبرها

-0.47

hombo

-0.46

xbox

-0.46

 holi

-0.46

POSITIVE LOGITS

Архівовано

0.83

Hochspringen

0.78

 CreateTagHelper

0.72

tvguidetime

0.72

ագրություններ

0.70

MemoryWarning

0.70

 autorytatywna

0.68

 Exactos

0.67

 NSCoder

0.65

htdocs

0.62

Activations Density 0.094%

references to specific software components or identifiers

No Comments

No Known Activations