INDEX

Explanations

mentions of actors and their careers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 operation

-0.38

נטרנט

-0.34

 implementation

-0.33

Brainz

-0.33

 Bakker

-0.33

 implement

-0.32

 operational

-0.32

 demonstration

-0.32

 position

-0.32

 summary

-0.32

POSITIVE LOGITS

 Actors

0.94

 actor

0.92

 actors

0.90

 Actor

0.84

Actors

0.83

Actor

0.82

 actresses

0.80

 actress

0.79

actors

0.75

 aktor

0.75

Activations Density 0.233%

mentions of actors and their careers

No Comments

No Known Activations