INDEX

Explanations

words or phrases that only appear in scientific articles

oai_token-act-pair · gemini-2.0-flash

roots

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 ―――――

-0.68

 Majefty

-0.66

"""

-0.66

 Monfieur

-0.66

 myſelf

-0.65

 doubtnut

-0.64

Vidite

-0.63

Efq

-0.63

 stiefel

-0.63

UnsafeEnabled

-0.63

POSITIVE LOGITS

<bos>

0.57

on

0.49

ORES

0.47

__(/*!

0.45

 komen

0.45

ņas

0.43

多了

0.41

Vanjske

0.41

shub

0.40

imgur

0.40

Activations Density 8.932%

words or phrases that only appear in scientific articles

roots

No Comments

No Known Activations