INDEX

Explanations

large numerical values or measurements

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

Punctuation marks and special characters

np_acts-logits-general · gemini-2.0-flash

punctuation or sentence end

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

 autorytatywna

-0.94

 Audiodateien

-0.90

Portale

-0.88

ÁND

-0.80

ECONDS

-0.79

VERTISEMENT

-0.79

eſ

-0.78

ſem

-0.78

ſſer

-0.78

eſt

-0.78

POSITIVE LOGITS

0.66

0.61

。

0.60

0.58

0.56

।

0.56

0.55

Activations Density 0.597%

large numerical values or measurements

Punctuation marks and special characters

punctuation or sentence end

No Comments

No Known Activations