INDEX

Explanations

technical terms related to APIs or programming frameworks

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

Followed by a letter

np_acts-logits-general · gemini-2.0-flash

tokens like N, ON, EN

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

WEBPACK

-0.63

جغرافيا

-0.60

TRAILING

-0.55

esModule

-0.49

 Chwiliwch

-0.49

 Santi

-0.47

 colic

-0.46

Jereo

-0.46

QMetaType

-0.45

 Grün

-0.45

POSITIVE LOGITS

umer

0.71

umbers

0.68

umber

0.66

ote

0.60

ormal

0.58

ative

0.58

amed

0.58

uclear

0.57

avigation

0.56

umpy

0.56

Activations Density 0.270%

technical terms related to APIs or programming frameworks

Followed by a letter

tokens like N, ON, EN

No Comments

No Known Activations