INDEX

Explanations

names of places and individuals, often in a narrative or report format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 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

↵↵

-0.30

多

-0.25

-0.24

setValues

-0.24

 Стали

-0.24

↵

-0.23

use

-0.23

 object

-0.23

POSITIVE LOGITS

ロウィン

1.02

featureID

1.00

MigrationBuilder

0.93

 مشين

0.91

нгред

0.89

 ſind

0.89

 zwiſchen

0.88

 CreateTagHelper

0.87

੝

0.86

 témoig

0.86

Activations Density 2.548%

names of places and individuals, often in a narrative or report format

No Comments

No Known Activations