INDEX

Explanations

references to people, places, or entities in a context that appears to involve interactions or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

IntoConstraints

-0.97

 Vikipedi

-0.92

 propOrder

-0.91

 BIBSYS

-0.87

VIAF

-0.85

 >=",

-0.83

afficheront

-0.81

extAlignment

-0.80

EndGlobalSection

-0.78

 autorytatywna

-0.76

POSITIVE LOGITS

#+#

0.70

 francès

0.61

:+:

0.61

 Symfony

0.56

 pomo

0.55

Initializable

0.52

 Geoff

0.52

 Fournier

0.51

Geoff

0.51

Scénario

0.50

Activations Density 1.681%

references to people, places, or entities in a context that appears to involve interactions or characteristics

No Comments

No Known Activations