INDEX

Explanations

numerical data and technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 bezeichneter

-0.83

UserScript

-0.82

XmlAccessType

-0.81

enumi

-0.76

principalColumn

-0.73

 AssemblyCompany

-0.73

-0.72

…]

-0.69

 FetchType

-0.69

็จ

-0.69

POSITIVE LOGITS

 lenker

0.63

0.56

nonatomic

0.54

0.51

0.50

0.49

0.47

ής

0.47

Activations Density 0.484%

numerical data and technical specifications

No Comments

No Known Activations