INDEX

Explanations

words related to permission or enabling actions

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

"allow" or variations of it

np_acts-logits-general · gemini-2.0-flash

allow or permit

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

tagHelperRunner

-0.80

XmlAccessType

-0.76

SessionFactory

-0.76

下载附件

-0.70

 jLabel

-0.70

 CreateTagHelper

-0.69

 كومونز

-0.69

 AssemblyCompany

-0.67

?»

-0.67

AndEndTag

-0.65

POSITIVE LOGITS

ALLOW

1.05

 ALLOW

1.01

 Allows

0.99

 allows

0.96

 Allow

0.95

 allow

0.92

Allows

0.91

 allowed

0.90

 permits

0.88

 allowing

0.88

Activations Density 0.108%

words related to permission or enabling actions

"allow" or variations of it

allow or permit

No Comments

No Known Activations