INDEX

Explanations

complex concepts that require exploration or clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Revenir

-0.63

ArrowToggle

-0.61

 فريبيس

-0.60

bitField

-0.59

<bos>

-0.57

 panties

-0.56

getValueAt

-0.56

resizingMask

-0.55

ScopeManager

-0.54

 Мексичка

-0.53

POSITIVE LOGITS

0.66

wami

0.55

ién

0.55

ミナル

0.52

ại

0.52

ibol

0.50

isst

0.49

rophilic

0.49

functioning

0.49

nolia

0.49

Activations Density 0.842%

complex concepts that require exploration or clarification

No Comments

No Known Activations