INDEX

Explanations

phrases that describe different things having something in common or related

oai_token-act-pair · gemini-2.0-flash

programming-related terminology or phrases

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

something

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

Negative Logits

 having

-1.37

having

-1.28

Having

-1.17

had

-1.16

 Having

-1.16

have

-1.13

 Have

-1.07

Have

-1.07

 have

-1.06

 HAVING

-1.05

POSITIVE LOGITS

 AssemblyCulture

0.78

ⓧ

0.77

DeleteBehavior

0.75

Démographie

0.70

Demografía

0.62

aarrggbb

0.59

SequentialGroup

0.59

RegressionTest

0.58

woor

0.58

Nazionale

0.57

Activations Density 0.694%

phrases that describe different things having something in common or related

programming-related terminology or phrases

something

No Known Activations