INDEX

Explanations

words related to product descriptions, often mentioning parts and features

oai_token-act-pair · gemini-2.0-flash

building materials

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Majefty

-0.95

Efq

-0.92

 Jefus

-0.88

 purpoſe

-0.87

 Shakspeare

-0.85

ſelves

-0.84

 Chriftian

-0.84

ſelf

-0.84

 Anſ

-0.83

 pleaſure

-0.83

POSITIVE LOGITS

iron

0.45

 Stone

0.37

 iron

0.36

 Iron

0.34

 stone

0.33

 crisp

0.33

 Glass

0.33

hyd

0.32

Cooler

0.32

 copper

0.30

Activations Density 23.240%

words related to product descriptions, often mentioning parts and features

building materials

No Comments

No Known Activations