INDEX

Explanations

terms and phrases related to programming and documentation formats

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 scolaires

-0.67

webElementXpaths

-0.64

-0.62

 asiatique

-0.62

 hâte

-0.61

 noastre

-0.60

 nationaux

-0.59

 NDEBUG

-0.58

 normaux

-0.58

цездатний

-0.57

POSITIVE LOGITS

colgroup

1.09

 colspan

0.64

migrationBuilder

0.62

/>

0.60

XmlType

0.58

&+

0.56

UNRELATED

0.55

SequentialGroup

0.54

rader

0.53

lossary

0.53

Activations Density 0.019%

terms and phrases related to programming and documentation formats

No Comments

No Known Activations