INDEX

Explanations

words related to stories and documented accounts

oai_token-act-pair · gemini-2.0-flash

storytelling/narratives

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

::~

-0.60

EndInit

-0.52

 nông

-0.50

ennifer

-0.50

ByName

-0.50

zheim

-0.49

 geze

-0.47

macam

-0.47

CORRECT

-0.46

حياته

-0.46

POSITIVE LOGITS

<bos>

0.89

 anecdote

0.70

Autoritní

0.68

 anecdotes

0.67

клопе

0.61

 utafitiHapana

0.60

__()

0.60

 CURIAM

0.59

 tartalomajánló

0.59

uxxxx

0.59

Activations Density 1.283%

words related to stories and documented accounts

storytelling/narratives

No Comments

No Known Activations