INDEX

Explanations

references to naming or designation of entities

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

例句

-0.76

 Reverso

-0.71

 parishes

-0.65

 recyclerView

-0.65

 zeigten

-0.63

''');

-0.62

Hyde

-0.62

/");

-0.61

uttavia

-0.61

Badger

-0.61

POSITIVE LOGITS

 names

1.55

 name

1.36

 Names

1.33

 NAMES

1.24

 NAME

1.21

 named

1.19

names

1.18

 Name

1.14

naming

1.06

Names

1.06

Activations Density 0.098%

references to naming or designation of entities

No Comments

No Known Activations