INDEX

Explanations

headings and boolean data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ing

-1.24

ة

-0.94

 Gentry

-0.94

-0.91

ς

-0.87

ené

-0.83

ená

-0.77

ING

-0.73

GLOBALS

-0.73

ی

-0.72

POSITIVE LOGITS

<h1>

1.65

__*/

0.98

 Momb

0.98

 Palae

0.93

roaches

0.92

iastical

0.90

anueva

0.89

 DOOM

0.89

 Moos

0.88

UpInside

0.88

Activations Density 0.136%

headings and boolean data types

No Comments

No Known Activations