INDEX

Explanations

a mix of computer code, math notation, and biological notation, as well as short words such as "to", "in", "and", "is"

oai_token-act-pair · gemini-2.0-flash

code syntax and method calls

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

Code snippets

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagHelper

-0.55

-0.54

-0.52

-0.50

--

-0.50

–

-0.49

—

-0.49

POSITIVE LOGITS

".

0.84

 Forumite

0.83

 мәкал

0.82

?».

0.80

Personendaten

0.78

 bezeichneter

0.78

 nonUne

0.77

 IBRARY

0.76

`;

0.75

afficheront

0.75

Activations Density 6.730%

a mix of computer code, math notation, and biological notation, as well as short words such as "to", "in", "and", "is"

code syntax and method calls

Code snippets

No Comments

No Known Activations