INDEX

Explanations

terms related to programming or computer security vulnerabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

-0.90

setupUi

-0.87

الحياه

-0.84

RenderAtEndOf

-0.84

 CURIAM

-0.76

География

-0.73

sizeCache

-0.73

dafx

-0.72

ConstraintMaker

-0.72

POSITIVE LOGITS

imp

0.40

 يلي

0.40

tc

0.40

rha

0.39

ei

0.39

 mathe

0.38

Ведь

0.37

Invoker

0.37

์

0.36

nz

0.35

Activations Density 0.041%

terms related to programming or computer security vulnerabilities

No Comments

No Known Activations