INDEX

Explanations

reviews and comments about specific products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

“

-0.62

-0.59

-0.53

tzw

-0.46

かわ

-0.46

one

-0.45

 конце

-0.45

„

-0.44

mayer

-0.43

POSITIVE LOGITS

 Majefty

1.09

脚注の使い方

1.08

новништво

1.08

 autorytatywna

1.06

RenderAtEndOf

1.06

posedge

1.02

دانشنامهٔ

0.99

 Normdatei

0.97

 Walkover

0.97

 AssemblyCulture

0.95

Activations Density 0.216%

reviews and comments about specific products or services

No Comments

No Known Activations