INDEX

Explanations

instances of the letter 'N' in different contexts

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

starting with "N" followed by another letter

np_acts-logits-general · gemini-2.0-flash

n followed by various characters

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

ampton

-0.66

 صوتيه

-0.59

mitter

-0.58

InjectAttribute

-0.58

offsetof

-0.58

 ©️

-0.55

ManyToOne

-0.55

ÃO

-0.54

ford

-0.53

enumi

-0.53

POSITIVE LOGITS

transQ

0.51

addCriterion

0.46

السكان

0.46

étit

0.46

NNNN

0.45

ATIVE

0.45

AutoScaleMode

0.43

司

0.43

GeoNames

0.43

elbow

0.43

Activations Density 0.194%

instances of the letter 'N' in different contexts

starting with "N" followed by another letter

n followed by various characters

No Comments

No Known Activations