INDEX

Explanations

elements associated with positive attributes and benefits

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

évaluateur

-0.96

ConstraintMaker

-0.90

 HttpNotFound

-0.82

ngdoc

-0.81

WaitGroup

-0.74

 unknownFields

-0.74

 للاسماء

-0.74

ftagPool

-0.74

 gyhoeddwyd

-0.74

WebServlet

-0.73

POSITIVE LOGITS

 тоже

0.68

too

0.65

 ebenfalls

0.53

についても

0.52

のも

0.51

 nữa

0.51

こちらも

0.49

これも

0.49

さも

0.48

ことも

0.48

Activations Density 0.546%

elements associated with positive attributes and benefits

No Comments

No Known Activations