INDEX

Explanations

statements or claims related to events or responsibilities

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

 Reddy

-0.57

tvguidetime

-0.56

 Holm

-0.56

 отдельно

-0.56

TagHelpers

-0.54

IntoConstraints

-0.53

 Lite

-0.51

Fio

-0.51

cide

-0.50

ponses

-0.50

POSITIVE LOGITS

awaiter

0.81

 >=",

0.71

 Chwiliwch

0.65

رشف

0.64

 utafiti

0.64

цездатний

0.64

MigrationBuilder

0.63

MessageTagHelper

0.63

الحياه

0.62

MessageOf

0.61

Activations Density 0.266%

statements or claims related to events or responsibilities

No Comments

No Known Activations