INDEX

Explanations

references to influential authors and their notable works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

支

-0.37

 словарь

-0.36

 Accelerated

-0.35

Autoritní

-0.35

 Present

-0.33

classmethod

-0.33

 Brunnen

-0.33

Já

-0.33

ونه

-0.33

private

-0.33

POSITIVE LOGITS

 propOrder

0.65

BufferException

0.58

hoeddwyd

0.57

richTextPanel

0.56

 FetchType

0.54

 Picchu

0.54

 influential

0.54

MLLoader

0.53

 EconPapers

0.50

 prompting

0.49

Activations Density 0.562%

references to influential authors and their notable works

No Comments

No Known Activations