INDEX

Explanations

terms related to authentication and security in programming contexts

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

secret password

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

-0.77

+#+#

-0.73

 للاسماء

-0.72

httphttps

-0.70

LabelTagHelper

-0.70

SequentialGroup

-0.69

ftagPool

-0.68

 utafitiHapana

-0.66

ValueStyle

-0.66

AndEndTag

-0.65

POSITIVE LOGITS

PasswordField

0.61

 Secret

0.49

 Geheim

0.47

 mystery

0.46

Secret

0.45

 hidden

0.44

 password

0.43

 secret

0.42

 mysterious

0.42

password

0.41

Activations Density 0.001%

terms related to authentication and security in programming contexts

secret password

No Comments

No Known Activations