INDEX

Explanations

key-value pair indicators within a dataset or coding structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 plus

-0.53

plus

-0.53

 Mail

-0.53

Mail

-0.50

VIAF

-0.48

 arter

-0.47

GAA

-0.46

 Gunther

-0.44

 itſelf

-0.43

 đỡ

-0.43

POSITIVE LOGITS

posedge

1.00

 AssemblyTitle

0.92

TagMode

0.91

enumi

0.89

migrationBuilder

0.85

 consultato

0.84

principalColumn

0.84

gdx

0.82

__*/

0.82

+#+#

0.81

Activations Density 0.103%

key-value pair indicators within a dataset or coding structure

No Comments

No Known Activations