INDEX

Explanations

phrases related to algorithms or mathematical models

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

RTDA

-0.74

 uintptr

-0.74

ffindor

-0.68

APORE

-0.66

riwal

-0.66

 Christendom

-0.64

Vidite

-0.64

iança

-0.63

NewUrlParser

-0.63

Jîn

-0.62

POSITIVE LOGITS

ValueStyle

0.84

 تضيفلها

0.71

<eos>

0.70

abestanden

0.70

WebVitals

0.63

 CanadaChoose

0.63

>");

0.59

 насељу

0.59

AnimationsModule

0.57

انجليز

0.54

Activations Density 1.036%

phrases related to algorithms or mathematical models

No Comments

No Known Activations