INDEX

Explanations

terms related to measurements and comparisons in scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 disambiguazione

-0.95

 quæ

-0.88

DoubleQuotes

-0.85

UserScript

-0.79

 Monfieur

-0.77

 للمعارف

-0.77

 iſt

-0.76

 myſelf

-0.74

 auffi

-0.73

 متعلقه

-0.72

POSITIVE LOGITS

Prefs

0.47

0.44

expiresIn

0.44

IMDG

0.41

nitzer

0.41

ridae

0.41

mycin

0.40

LEncoder

0.40

χος

0.39

Activations Density 0.520%

terms related to measurements and comparisons in scientific or technical contexts

No Comments

No Known Activations