INDEX

Explanations

references to roles and their significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

GEBURTSDATUM

-0.86

DebuggerNonUser

-0.84

 disambiguazione

-0.70

ImageContext

-0.69

addCriterion

-0.67

TProtocol

-0.66

 <<<<<<<<<<<<<<

-0.62

latego

-0.62

WebpackPlugin

-0.62

RenderAtEndOf

-0.61

POSITIVE LOGITS

 posed

0.64

 onBind

0.62

 joué

0.54

 played

0.53

 ervan

0.53

 exerted

0.49

 attaching

0.45

posed

0.43

zlich

0.43

SourceChecksum

0.42

Activations Density 0.441%

references to roles and their significance in various contexts

No Comments

No Known Activations