INDEX

Explanations

phrases related to declining comments or information

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

UserScript

-0.59

correctly

-0.59

 internetowa

-0.58

fjspx

-0.54

Успе

-0.52

 parcialmente

-0.50

 politely

-0.50

 posib

-0.50

blurRadius

-0.49

 possibili

-0.48

POSITIVE LOGITS

 comment

0.75

 Comment

0.71

 commenting

0.71

 formally

0.67

 specific

0.65

 definitive

0.64

 official

0.62

 COMMENT

0.62

specific

0.61

 conclusive

0.61

Activations Density 0.630%

phrases related to declining comments or information

No Comments

No Known Activations