INDEX

Explanations

technical terms related to API requests and configurations

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

Code, settings, or configurations

np_acts-logits-general · gemini-2.0-flash

assuming default settings

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

ledge

-0.49

SetString

-0.47

milla

-0.46

erville

-0.45

 erken

-0.45

出版年

-0.45

Incorrect

-0.44

 poudre

-0.44

 发表于

-0.44

awtextra

-0.43

POSITIVE LOGITS

 current

0.73

Personendaten

0.69

current

0.68

 Jefus

0.66

 default

0.65

 myſelf

0.62

 EconPapers

0.61

ſelf

0.61

 MainAxisSize

0.61

 preſent

0.60

Activations Density 0.582%

technical terms related to API requests and configurations

Code, settings, or configurations

assuming default settings

No Comments

No Known Activations