INDEX

Explanations

terms related to bricks and pauses in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Geb

-0.69

ernsey

-0.68

ker

-0.66

Cra

-0.66

Tob

-0.65

ItemLayout

-0.65

kle

-0.64

Tob

-0.62

lable

-0.60

Embeddable

-0.60

POSITIVE LOGITS

 bounces

0.94

 bouncing

0.94

 Banners

0.93

 Bricks

0.90

 fade

0.90

RenderAtEndOf

0.89

 ALICE

0.89

pause

0.88

 Banner

0.86

 bricks

0.86

Activations Density 0.083%

terms related to bricks and pauses in narratives

No Comments

No Known Activations