INDEX

Explanations

technical terms and data structures related to programming and coding contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-1.12

 CreateTagHelper

-1.07

 Савезне

-0.97

__':

-0.92

TagMode

-0.89

ьаж

-0.86

SourceChecksum

-0.85

 للاسماء

-0.84

fjspx

-0.82

RegistryLite

-0.81

POSITIVE LOGITS

multirow

0.52

too

0.51

 same

0.50

 също

0.44

 тоже

0.44

usermodel

0.40

 επίσης

0.39

 także

0.39

 recommandée

0.38

来歴

0.38

Activations Density 1.569%

technical terms and data structures related to programming and coding contexts

No Comments

No Known Activations