INDEX

Explanations

occurrences of the prefix "sw" in various contexts

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

starting with "Sw" or "sw"

np_acts-logits-general · gemini-2.0-flash

Sw- prefix

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

principalColumn

-0.58

neté

-0.57

UnusedPrivate

-0.56

 ProtoMessage

-0.56

martre

-0.54

ंदीखरीदारी

-0.53

 اطلع

-0.52

selves

-0.51

 continúas

-0.50

parsedMessage

-0.49

POSITIVE LOGITS

Sw

0.67

sw

0.67

Sw

0.66

 swam

0.56

RegistryLite

0.52

ScopeManager

0.52

Swish

0.51

 betweenstory

0.51

Autoritní

0.50

 Swanson

0.48

Activations Density 0.121%

occurrences of the prefix "sw" in various contexts

starting with "Sw" or "sw"

Sw- prefix

No Comments

No Known Activations