INDEX

Explanations

references to specific locations, particularly those associated with "San" in their names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

WebVitals

-1.05

 betweenstory

-1.04

 Roskov

-0.96

InjectAttribute

-0.92

 препратки

-0.89

 Guiana

-0.85

IContainer

-0.85

EDEFAULT

-0.85

 vVar

-0.84

]){

-0.84

POSITIVE LOGITS

San

1.41

San

1.28

SAN

1.22

 Sandi

1.16

 Sanford

1.10

SAN

1.10

san

1.10

san

1.01

 sanctions

0.97

 Sanctions

0.97

Activations Density 0.199%

references to specific locations, particularly those associated with "San" in their names

No Comments

No Known Activations