INDEX

Explanations

information related to bug reporting and tracking

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

Followed by words related to "bug" or "issue"

np_acts-logits-general · gemini-2.0-flash

bug and issue discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 contraband

-0.59

autoload

-0.59

 صوتيه

-0.53

createCanvas

-0.52

Inflater

-0.51

GOTREF

-0.51

CppMethod

-0.50

 Astra

-0.50

 Wicidata

-0.48

oubliez

-0.48

POSITIVE LOGITS

bug

1.15

Bug

1.07

 issue

1.04

 Issue

1.02

Bug

0.99

bug

0.96

issue

0.96

 ticket

0.94

Issue

0.93

ticket

0.85

Activations Density 0.657%

information related to bug reporting and tracking

Followed by words related to "bug" or "issue"

bug and issue discussion

No Comments

No Known Activations