INDEX

Explanations

references to programming objects and their properties or methods

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

aarrggbb

-0.98

 jScrollPane

-0.94

 resourceCulture

-0.86

aporation

-0.72

']],

-0.71

tisgarh

-0.70

sertation

-0.70

heça

-0.67

"];

-0.67

>";

-0.67

POSITIVE LOGITS

 myſelf

1.17

 Majefty

1.03

 Monfieur

1.03

 pleaſure

1.01

 itſelf

1.00

ſelf

0.98

ſelves

0.97

 Houſe

0.96

 Cæsar

0.93

 ſmall

0.93

Activations Density 0.857%

references to programming objects and their properties or methods

No Comments

No Known Activations