INDEX

Explanations

acronyms and abbreviations relevant to organizations, molecules, and specific scientific terminologies

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

อาด

-0.66

 AssemblyCompany

-0.62

 ویکی‌پدیا

-0.61

 Bioaccumulative

-0.59

leggio

-0.58

CWE

-0.58

 ویکی‌پدیای

-0.57

 GenerationType

-0.57

脚注の使い方

-0.57

ènement

-0.56

POSITIVE LOGITS

 purpoſe

0.79

évaluateur

0.79

 Theſe

0.70

 pleaſure

0.69

 ſta

0.69

 Anſ

0.68

 Reſ

0.67

 faſt

0.65

 Diſ

0.64

 leaſt

0.64

Activations Density 1.012%

acronyms and abbreviations relevant to organizations, molecules, and specific scientific terminologies

No Comments

No Known Activations