INDEX

Explanations

references to bugs needing information or clarification in a software context

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

CppMethod

-0.59

 contraband

-0.59

 Wicidata

-0.57

 صوتيه

-0.55

ContentAsync

-0.54

WithFormat

-0.54

GEBURTSDATUM

-0.54

createCanvas

-0.53

autoload

-0.52

िखित

-0.52

POSITIVE LOGITS

bug

1.16

 issue

1.10

Bug

1.06

 Issue

1.05

issue

1.01

Bug

0.97

bug

0.95

Issue

0.95

 ticket

0.94

ticket

0.91

Activations Density 0.577%

references to bugs needing information or clarification in a software context

No Comments

No Known Activations