INDEX

Explanations

abbreviations, acronyms, and specific codes related to technical or scientific content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

GraphicsUnit

-0.69

HasAnnotation

-0.57

IBOutlet

-0.53

 purpose

-0.52

 main

-0.50

ctron

-0.49

ƒ

-0.48

 surla

-0.47

<tfoot>

-0.47

POSITIVE LOGITS

 reaſon

0.87

 pleaſure

0.84

 myſelf

0.81

 ſta

0.80

 ſtate

0.79

 ſay

0.78

 cauſe

0.77

 ſmall

0.77

 Diſ

0.76

 ſtre

0.76

Activations Density 0.591%

abbreviations, acronyms, and specific codes related to technical or scientific content

No Comments

No Known Activations