INDEX

Explanations

code snippets in languages like Go, specifically looking for import statements, package declarations, and build tags

oai_token-act-pair · gemini-2.0-flash

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

länge

-0.50

 ويكيميديا

-0.50

\{\\

-0.49

QualifiedName

-0.49

 ſta

-0.48

 Kinetics

-0.47

 Understanding

-0.47

inetics

-0.47

anship

-0.46

 Klassi

-0.46

POSITIVE LOGITS

terraform

0.73

#+#

0.64

ioutil

0.62

BeginContext

0.60

TProtocol

0.58

:+:

0.57

kháu

0.57

WriteTagHelper

0.56

AddTagHelper

0.55

gink

0.54

Activations Density 6.105%

code snippets in languages like Go, specifically looking for import statements, package declarations, and build tags

code

No Comments

No Known Activations