INDEX

Explanations

references to North American entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

AsUp

-0.48

thâu

-0.44

 Pública

-0.41

 needed

-0.40

cerv

-0.40

 diesmal

-0.39

tattoo

-0.39

telde

-0.39

 diesel

-0.39

POSITIVE LOGITS

ImageContext

0.80

+#+#

0.77

ymce

0.75

CodeAnalysis

0.72

 CanadaChoose

0.72

 Advocate

0.71

 advocate

0.70

原始内容存档于

0.70

DockStyle

0.70

Advocate

0.70

Activations Density 1.470%

references to North American entities or concepts

No Comments

No Known Activations