INDEX

Explanations

words related to computer algorithms, electronics, and mechanical devices

oai_token-act-pair · gemini-2.0-flash

random English words

np_token-act-pair-logits · gemini-2.0-flash

Computer science descriptions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.47

source

-0.46

hland

-0.45

 gener

-0.44

kes

-0.43

...

-0.43

Co

-0.42

hspace

-0.40

enge

-0.40

 nguyên

-0.40

POSITIVE LOGITS

Efq

1.06

 myſelf

1.02

 themſelves

0.92

 itſelf

0.91

 whoſe

0.88

 Monfieur

0.88

 himſelf

0.86

 Theſe

0.84

 Jefus

0.82

 uſed

0.80

Activations Density 4.612%

words related to computer algorithms, electronics, and mechanical devices

random English words

Computer science descriptions

No Comments

No Known Activations