INDEX

Explanations

elements related to schema definitions and object properties

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

Code snippets or configuration details

np_acts-logits-general · gemini-2.0-flash

JSON configuration or code keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 &___

-0.64

EDEFAULT

-0.55

 متعلقه

-0.51

DeleteMapping

-0.50

ようになります

-0.49

PutMapping

-0.48

_$

-0.48

 Relaciones

-0.46

gelijke

-0.45

Itoa

-0.45

POSITIVE LOGITS

 Мексичка

0.77

 Audiodateien

0.62

 XNUMX

0.62

 Waray

0.61

!")

0.61

+#+#

0.60

'},

0.60

NUMX

0.60

StoryboardSegue

0.59

GEBURTSDATUM

0.58

Activations Density 0.232%

elements related to schema definitions and object properties

Code snippets or configuration details

JSON configuration or code keywords

No Comments

No Known Activations