INDEX

Explanations

terms related to selections, examples, and publications in research or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

fillType

-0.37

setof

-0.33

 fiume

-0.33

 pernas

-0.33

原始内容存档

-0.31

 verhaal

-0.31

ward

-0.31

ambilan

-0.30

цездатний

-0.30

calça

-0.29

POSITIVE LOGITS

 examples

0.68

Auswahl

0.60

 Selected

0.58

 препратки

0.57

 misc

0.57

oughton

0.56

examples

0.56

 Examples

0.56

lccn

0.55

 Quelques

0.55

Activations Density 0.483%

terms related to selections, examples, and publications in research or academic contexts

No Comments

No Known Activations