INDEX

Explanations

references and citations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 الرياضيه

-0.72

ніципалі

-0.69

ніципа

-0.67

Demografie

-0.67

rrggbb

-0.66

idends

-0.65

المكان

-0.64

Solución

-0.63

kháu

-0.63

 للمعارف

-0.62

POSITIVE LOGITS

原始内容存档于

0.68

↑

0.66

SourceChecksum

0.62

GraphicsUnit

0.61

<eos>

0.59

addGap

0.59

 виправивши

0.54

rungsseite

0.52

klis

0.52

 BoxDecoration

0.51

Activations Density 0.214%

references and citations in the text

No Comments

No Known Activations