INDEX

Explanations

measurements and dimensions in various formats

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

 themſelves

-0.67

neſs

-0.64

 }}$}

-0.64

ıntı

-0.62

Referințe

-0.60

 rallado

-0.59

eseorang

-0.58

ſelf

-0.58

 himſelf

-0.57

POSITIVE LOGITS

/=

0.96

CPtr

0.83

帖最后由

0.74

SpringBootTest

0.72

 AssemblyCulture

0.72

AddWithValue

0.70

axa

0.69

mopol

0.68

 بتاريخ

0.67

valents

0.67

Activations Density 0.586%

measurements and dimensions in various formats

No Comments

No Known Activations