INDEX

Explanations

mathematical symbols and notations related to equations and variables

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bezeichneter

-0.84

//

-0.74

kaner

-0.72

'}>

-0.71

Personendaten

-0.68

boldmath

-0.68

<eos>

-0.67

)}$

-0.67

Datuak

-0.66

ValueStyle

-0.65

POSITIVE LOGITS

UseVisualStyle

0.82

danno

0.70

 Bacchus

0.70

inigte

0.69

hdysval

0.68

 Pelham

0.68

 oorsp

0.67

 Balkans

0.67

 Azer

0.66

$_"

0.66

Activations Density 0.705%

mathematical symbols and notations related to equations and variables

No Comments

No Known Activations