INDEX

Explanations

terms related to software vulnerabilities, specifically those associated with buffer overflow issues

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

Code snippets or comments

np_acts-logits-general · gemini-2.0-flash

code safety and fixes

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

localctx

-0.46

pa

-0.42

 auto

-0.40

 nowo

-0.39

re

-0.38

auto

-0.38

 authorised

-0.38

 comprehensively

-0.37

 conten

-0.37

rost

-0.37

POSITIVE LOGITS

CWE

1.49

CWE

1.01

 AssemblyTitle

0.78

 doInBackground

0.76

 Савезне

0.75

 Majefty

0.72

 يتيمه

0.72

InputBorder

0.72

ⓧ

0.71

RenderAtEndOf

0.71

Activations Density 0.036%

terms related to software vulnerabilities, specifically those associated with buffer overflow issues

Code snippets or comments

code safety and fixes

No Comments

No Known Activations