INDEX

Explanations

terms related to research methodologies and frameworks

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

 betweenstory

-0.45

 onPage

-0.45

-0.43

elang

-0.43

 dalle

-0.42

↵

-0.41

at

-0.41

-0.40

isso

-0.40

POSITIVE LOGITS

 Majefty

1.07

:✨

1.02

 للاسماء

0.97

InjectAttribute

0.94

Efq

0.92

 Normdatei

0.92

SharedCtor

0.91

 Jefus

0.89

 Reſ

0.88

 purpoſe

0.87

Activations Density 0.654%

terms related to research methodologies and frameworks

No Comments

No Known Activations