INDEX

Explanations

code snippets using C, particularly related to file or device input/output and error handling

oai_token-act-pair · gemini-2.0-flash

Code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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

WireFormatLite

-0.65

 виправивши

-0.59

pexpr

-0.52

phrine

-0.51

PositiveButton

-0.49

Diweddarwch

-0.49

ophageal

-0.49

ocardio

-0.49

पया

-0.49

BURGH

-0.47

POSITIVE LOGITS

"]));

0.52

 &___

0.52

0.50

Adapters

0.49

ngu

0.48

VPB

0.48

èbres

0.47

=[];

0.47

msgTypes

0.47

okovic

0.46

Activations Density 3.581%

code snippets using C, particularly related to file or device input/output and error handling

Code snippets

No Comments

No Known Activations