INDEX

Explanations

discussions about the acting profession, including references to 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-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Similar

-0.31

 lệ

-0.30

↵↵

-0.29

 diser

-0.29

 Office

-0.29

period

-0.28

rita

-0.28

 office

-0.28

 Ochoa

-0.28

ö

-0.27

POSITIVE LOGITS

 actor

0.74

 Actors

0.73

 Casting

0.70

 actors

0.70

 castings

0.67

 itſelf

0.66

ſelves

0.66

MLLoader

0.65

Casting

0.65

 Actor

0.64

Activations Density 0.140%

discussions about the acting profession, including references to actors and their careers

No Comments

No Known Activations