INDEX

Explanations

hexadecimal numbers that start with "0x7"

oai_token-act-pair · gemini-2.0-flash

specific identifiers or keywords in code

np_token-act-pair-logits · gpt-4o-mini

7

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

orithm

-0.59

formatics

-0.57

pung

-0.55

mación

-0.52

icap

-0.52

]--;

-0.52

באנגלית

-0.51

vass

-0.51

 Filed

-0.50

igenous

-0.50

POSITIVE LOGITS

LookAnd

0.65

windowFixed

0.60

UrlResolution

0.57

 pinulongan

0.56

✨:

0.54

TagMode

0.54

#+#

0.54

 estimés

0.53

 Idiot

0.51

 nahilalakip

0.50

Activations Density 0.851%

hexadecimal numbers that start with "0x7"

specific identifiers or keywords in code

7

No Comments

No Known Activations