INDEX

Explanations

none of the specified terms or concepts in the document

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

preceding punctuation

np_acts-logits-general · gemini-2.0-flash

certain words followed by punctuation

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

IGENCE

-0.51

dem

-0.44

OuterClass

-0.42

 entro

-0.41

 maille

-0.41

vid

-0.41

ne

-0.41

adpleegd

-0.41

 Insee

-0.41

ple

-0.40

POSITIVE LOGITS

InjectAttribute

0.93

 الحره

0.88

UserScript

0.79

 Cæsar

0.79

 nahilalakip

0.77

Hentet

0.74

 vectorstock

0.72

principalColumn

0.68

 itſelf

0.68

 Majefty

0.67

Activations Density 0.101%

none of the specified terms or concepts in the document

preceding punctuation

certain words followed by punctuation

No Comments

No Known Activations