INDEX

Explanations

specific mathematical symbols and notation

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

 surla

-1.02

-0.82

begin

-0.81

 Paglinawan

-0.74

mathrm

-0.67

<eos>

-0.62

GEBURTSDATUM

-0.61

MathML

-0.61

enumerate

-0.60

POSITIVE LOGITS

 itſelf

0.89

$_"

0.86

moiselle

0.82

neſs

0.81

 himſelf

0.81

ſelf

0.80

*/;

0.79

Efq

0.79

 Majefty

0.76

 purpoſe

0.76

Activations Density 3.510%

specific mathematical symbols and notation

No Comments

No Known Activations