INDEX

Explanations

expressions related to seriousness and significant themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 NSCoder

-0.50

 întâ

-0.49

DockStyle

-0.48

mobileqq

-0.46

codegen

-0.44

apimachinery

-0.44

‚¬

-0.42

 manifestly

-0.42

 freely

-0.42

pam

-0.42

POSITIVE LOGITS

 somber

0.86

 sober

0.85

sober

0.79

 Sober

0.72

 utilitarian

0.70

 drab

0.69

 austere

0.69

 grim

0.69

 sobriety

0.67

 boring

0.67

Activations Density 0.518%

expressions related to seriousness and significant themes

No Comments

No Known Activations