INDEX

Explanations

negative descriptors and expressions of dissatisfaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

-0.54

 égale

-0.49

 पास

-0.47

is

-0.47

artney

-0.46

ดับ

-0.44

 financières

-0.43

 loisirs

-0.43

 access

-0.42

…

-0.42

POSITIVE LOGITS

LookAnd

1.08

ArrowToggle

0.98

 MainAxisSize

0.97

RegressionTest

0.93

SharedDtor

0.90

IUrlHelper

0.81

queryInterface

0.79

 Савезне

0.79

 SwitchCompat

0.78

 ModelRenderer

0.77

Activations Density 0.222%

negative descriptors and expressions of dissatisfaction

No Comments

No Known Activations