INDEX

Explanations

words and phrases indicating conditions, results, or logical connections

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 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

Efq

-1.51

^(@)

-1.25

 Majefty

-1.25

 ་་

-1.24

$_"

-1.23

NUMX

-1.22

 photolibrary

-1.22

 Jefus

-1.21

 ſeveral

-1.20

 Monfieur

-1.20

POSITIVE LOGITS

1.11

0.83

0.81

0.79

(!

0.77

<eos>

0.77

0.76

("

0.74

0.71

0.68

Activations Density 0.509%

words and phrases indicating conditions, results, or logical connections

No Comments

No Known Activations

words and phrases indicating conditions, results, or logical connections

No Comments

No Known Activations