INDEX

Explanations

code syntax

oai_token-act-pair · gemini-2.0-flash

technical programming terms

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

math symbols

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

Hochspringen

-0.52

例文帳に追加

-0.50

 berupa

-0.47

 thân

-0.47

/');

-0.46

])));

-0.45

انيف

-0.45

ligen

-0.45

 bezeichneter

-0.44

IntoConstraints

-0.43

POSITIVE LOGITS

Personendaten

0.75

 كومونز

0.71

LLocation

0.66

AddTagHelper

0.64

 onBind

0.62

IBarButtonItem

0.61

 SqlParameter

0.61

 SqlCommand

0.59

 typelib

0.59

PreferredItem

0.59

Activations Density 3.644%

code syntax

technical programming terms

math symbols

No Comments

No Known Activations