INDEX

Explanations

actions and activities related to interaction and engagement

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

fikasi

-0.65

rsiniz

-0.61

pyrene

-0.54

 Zaragoza

-0.54

ければ

-0.53

onauts

-0.52

nO

-0.51

PLANATION

-0.50

 řek

-0.50

ậu

-0.50

POSITIVE LOGITS

GEBURTSDATUM

0.93

 nahilalakip

0.92

RenderAtEndOf

0.90

UnusedPrivate

0.87

RepeatedField

0.85

 doing

0.80

 autorytatywna

0.79

+#+

0.77

AndEndTag

0.77

دانشنامهٔ

0.76

Activations Density 0.708%

actions and activities related to interaction and engagement

No Comments

No Known Activations