INDEX

Explanations

terms related to encryption

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

encrypted connection

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 himſelf

-0.71

 themſelves

-0.66

 Houſe

-0.63

 myſelf

-0.60

 Majefty

-0.57

 unggul

-0.54

 mijne

-0.54

 itſelf

-0.53

 Consejos

-0.53

ſelves

-0.52

POSITIVE LOGITS

encrypted

1.70

 encrypted

1.55

Encrypted

1.39

crypted

1.19

 encrypt

0.85

 Encrypt

0.77

encrypt

0.77

Encrypt

0.69

 صوتيه

0.65

 hashed

0.54

Activations Density 0.002%

terms related to encryption

encrypted connection

No Comments

No Known Activations