INDEX

Explanations

phrases related to refusals to comment or provide information

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

Declined to comment or return calls

np_acts-logits-general · gemini-2.0-flash

no response declined

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

WebElementEntity

-0.61

 nahilalakip

-0.53

wpi

-0.52

 Normdatei

-0.52

ynh

-0.49

AddTagHelper

-0.49

Priority

-0.46

DOES

-0.44

ngx

-0.44

ace

-0.43

POSITIVE LOGITS

 مشين

0.73

:]:

0.66

contentLoaded

0.66

InputBorder

0.62

balleur

0.61

posedge

0.60

IntoConstraints

0.60

 comment

0.59

 سكانية

0.59

Filmographie

0.57

Activations Density 0.075%

phrases related to refusals to comment or provide information

Declined to comment or return calls

no response declined

No Comments

No Known Activations