INDEX

Explanations

names and terms related to specific individuals or entities in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Révolution

-0.84

-0.83

ness

-0.80

 leçon

-0.80

PathParam

-0.76

 chauss

-0.75

Personendaten

-0.75

 pitié

-0.73

 casquette

-0.72

POSITIVE LOGITS

ede

1.09

ADE

1.09

CIE

1.06

Mane

1.04

CME

1.03

 Dore

1.02

ATE

1.02

Rade

1.00

MIME

0.99

 SAGE

0.98

Activations Density 4.270%

names and terms related to specific individuals or entities in a document

No Comments

No Known Activations