INDEX

Explanations

references to books, especially story collections and reading

oai_token-act-pair · gemini-2.0-flash

technical terms or jargon

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

short stories

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

Enllaces

-0.74

ConstraintMaker

-0.66

RectangleBorder

-0.59

 CGRectMake

-0.57

endpush

-0.57

});*/

-0.56

 beginnetje

-0.56

 joindre

-0.55

AccessorTable

-0.54

CGRectMake

-0.54

POSITIVE LOGITS

RegisterType

0.60

 short

0.53

 vapeur

0.50

cerita

0.49

SBATCH

0.47

########.

0.47

 remarqué

0.47

 Caballero

0.47

 Stream

0.45

ResumeLayout

0.44

Activations Density 2.720%

references to books, especially story collections and reading

technical terms or jargon

short stories

No Comments

No Known Activations