INDEX

Explanations

words or phrases related to logical structures and principles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 desmotivaciones

-0.68

 Económica

-0.58

 littéraire

-0.54

 armées

-0.54

 económicas

-0.50

 procesu

-0.50

 psicológica

-0.50

 armée

-0.49

 Gegend

-0.49

 motocicletas

-0.49

POSITIVE LOGITS

 clicked

0.78

Cue

0.66

clicked

0.66

rev

0.66

 clicks

0.64

Cue

0.63

deb

0.63

 Click

0.59

cue

0.59

 تضيفلها

0.59

Activations Density 0.190%

words or phrases related to logical structures and principles

No Comments

No Known Activations