INDEX

Explanations

references to academic papers or proceedings, particularly focusing on citation formats and publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

bootstrapcdn

-0.67

 CreateTagHelper

-0.59

Пол

-0.53

 uitz

-0.53

ometrics

-0.53

 Пол

-0.52

rawtypes

-0.50

רח

-0.49

Cur

-0.49

婉

-0.48

POSITIVE LOGITS

StoryboardSegue

0.67

 AssemblyTitle

0.66

DockStyle

0.65

 مشين

0.61

Demografie

0.60

basicConfig

0.56

LEncoder

0.55

点此举报

0.55

 admittance

0.54

etak

0.52

Activations Density 0.149%

references to academic papers or proceedings, particularly focusing on citation formats and publication details

No Comments

No Known Activations