INDEX

Explanations

java io imports.

oai_token-act-pair · gemini-2.0-flash

code elements or identifiers in programming

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

Java code imports

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

^{+

-0.49

'('

-0.43

 يتيمه

-0.41

eyn

-0.40

PostMapping

-0.40

melis

-0.40

 Binnen

-0.39

dob

-0.38

πω

-0.38

 problemet

-0.38

POSITIVE LOGITS

 Paglinawan

0.80

tagHelperRunner

0.78

Personendaten

0.69

 AssemblyProduct

0.68

migrationBuilder

0.66

 EconPapers

0.66

enumii

0.64

webElementXpaths

0.62

EndContext

0.60

tagHelper

0.59

Activations Density 0.157%

java io imports.

code elements or identifiers in programming

Java code imports

No Comments

No Known Activations