INDEX

Explanations

references to royal titles and names

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

ISTIC

-0.61

ïsme

-0.58

istically

-0.55

 faſt

-0.54

 superpowers

-0.54

mering

-0.52

panning

-0.52

 Erfurt

-0.51

 diſt

-0.51

 pande

-0.51

POSITIVE LOGITS

PerformLayout

0.80

 héri

0.72

Personendaten

0.71

StoryboardSegue

0.68

ResumeLayout

0.65

 consultato

0.63

DeleteBehavior

0.62

 ProtoMessage

0.61

曖昧さ回避

0.61

tvguidetime

0.60

Activations Density 0.128%

references to royal titles and names

No Comments

No Known Activations