INDEX

Explanations

code snippets

oai_token-act-pair · gemini-2.0-flash

specialized resource tags or identifiers

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

code and configuration files

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

 erop

-0.47

)\}$

-0.45

UnusedPrivate

-0.45

פה

-0.45

]]);

-0.44

}));

-0.43

 nadal

-0.42

 normally

-0.42

 UITableViewCell

-0.42

εται

-0.42

POSITIVE LOGITS

 resourceCulture

0.78

modb

0.72

 متعلقه

0.68

AndEndTag

0.68

 Италијани

0.68

mphony

0.60

XmlAccessorType

0.60

 linkovi

0.60

 ujednoznacz

0.59

 disambiguazione

0.59

Activations Density 2.116%

code snippets

specialized resource tags or identifiers

code and configuration files

No Comments

No Known Activations

code snippets

specialized resource tags or identifiers

code and configuration files

No Comments

No Known Activations