INDEX

Explanations

terms related to measurements and calibrations in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-0.84

jsonwebtoken

-0.83

GEBURTSDATUM

-0.75

Vect

-0.75

 Mank

-0.72

 Grat

-0.71

icoot

-0.71

 Fisk

-0.71

 Kola

-0.70

 Piet

-0.70

POSITIVE LOGITS

SDI

0.80

 Easton

0.78

 '\\;'

0.77

 pars

0.76

 Theron

0.73

Mox

0.73

expandindo

0.73

 Lans

0.73

Keith

0.72

 Cougars

0.72

Activations Density 0.931%

terms related to measurements and calibrations in a scientific context

No Comments

No Known Activations