INDEX

Explanations

questions related to enabling or activating features in software or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 cherchés

-0.52

новништво

-0.49

lishes

-0.49

Trama

-0.48

 AttributeError

-0.48

tvguidetime

-0.47

ăr

-0.46

::*;

-0.46

 getPage

-0.46

 dates

-0.45

POSITIVE LOGITS

IUrlHelper

0.62

oplayer

0.61

 AspNetCore

0.52

 AssemblyProduct

0.52

Eminem

0.52

 crane

0.52

RepeatedField

0.49

 quir

0.49

art

0.48

Psi

0.48

Activations Density 0.062%

questions related to enabling or activating features in software or systems

No Comments

No Known Activations