INDEX

Explanations

numerical references to data or measurements associated with experiments or protocols

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

Numbers followed by specific units (keV, MHz, etc.)

np_acts-logits-general · gemini-2.0-flash

IP addresses and percentages

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

 متعلقه

-1.16

 Monfieur

-0.84

 Jefus

-0.83

 pleaſure

-0.82

 Majefty

-0.78

 ſtate

-0.78

 paroisse

-0.76

$_"

-0.74

AutoScaleMode

-0.74

 Reſ

-0.73

POSITIVE LOGITS

sor

0.54

UTIVE

0.51

Sor

0.49

 المعيارى

0.48

veless

0.47

os

0.46

cepcion

0.45

مانی

0.45

 catch

0.45

pes

0.42

Activations Density 0.196%

numerical references to data or measurements associated with experiments or protocols

Numbers followed by specific units (keV, MHz, etc.)

IP addresses and percentages

No Comments

No Known Activations