INDEX

Explanations

technical language related to computer memory and processors

oai_token-act-pair · gemini-2.0-flash

programming-related terms and constructs

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

computer memory addresses

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

 beginnetje

-0.76

uxxxx

-0.64

 EconPapers

-0.61

verwijspagina

-0.60

rungsseite

-0.59

unknownFields

-0.59

 cherchés

-0.58

adaptiveStyles

-0.57

MigrationBuilder

-0.55

RegistryLite

-0.55

POSITIVE LOGITS

 MainAxisSize

0.57

 localObject

0.51

ioutil

0.50

myra

0.47

doria

0.46

verständlich

0.46

HttpFoundation

0.45

isMethod

0.44

rump

0.44

ponses

0.44

Activations Density 5.914%

technical language related to computer memory and processors

programming-related terms and constructs

computer memory addresses

No Comments

No Known Activations