INDEX

Explanations

references to the word "Bur."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TintMode

-0.65

SerializedName

-0.64

 indios

-0.60

 Wikimedijinoj

-0.59

 Khanna

-0.58

 lentement

-0.56

bewerken

-0.56

ciating

-0.56

 puesta

-0.55

 autorytatywna

-0.54

POSITIVE LOGITS

bur

0.66

دانشنامهٔ

0.64

 EconPapers

0.63

bur

0.62

 invol

0.62

BUR

0.60

EAR

0.57

WithMany

0.56

 minimum

0.55

 deps

0.55

Activations Density 0.258%

references to the word "Bur."

No Comments

No Known Activations