INDEX

Explanations

structured data formats, particularly those resembling lists or dictionaries

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

Hexadecimal characters and hyphens

np_acts-logits-general · gemini-2.0-flash

hexadecimal ids

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

UnsafeEnabled

-0.59

PYX

-0.56

Бахар

-0.56

enschappelijke

-0.56

 LIRE

-0.54

Xna

-0.53

 فريبيس

-0.53

johtaja

-0.49

TagMode

-0.48

RetentionPolicy

-0.48

POSITIVE LOGITS

0.74

0.72

0.69

0.68

0.61

 onPostExecute

0.52

exitRule

0.50

dT

0.50

γμα

0.50

Activations Density 0.213%

structured data formats, particularly those resembling lists or dictionaries

Hexadecimal characters and hyphens

hexadecimal ids

No Comments

No Known Activations