INDEX

Explanations

references to leading or prominent entities and individuals across various fields

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SequentialGroup

-1.00

 sped

-0.56

xDB

-0.54

void

-0.51

getCause

-0.50

стма

-0.49

 Reeves

-0.49

IContainer

-0.48

ube

-0.48

τό

-0.48

POSITIVE LOGITS

IntoConstraints

0.96

 finest

0.82

 respected

0.78

 excellence

0.78

 estimés

0.74

 greateſt

0.73

Веду

0.72

 recognised

0.71

 reputable

0.71

 réput

0.71

Activations Density 0.180%

references to leading or prominent entities and individuals across various fields

No Comments

No Known Activations