INDEX

Explanations

words related to evaluation and outcomes in research contexts

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

MP

-0.33

ViewImports

-0.31

Red

-0.30

 cucchiaio

-0.30

ST

-0.29

sträger

-0.28

annan

-0.28

Tom

-0.28

CategoryId

-0.28

 fell

-0.27

POSITIVE LOGITS

transQ

0.77

PYX

0.72

onViewCreated

0.71

 незавершена

0.70

KommentareTeilen

0.65

 שוליים

0.61

 desmotivaciones

0.60

 onBind

0.59

 MainAxisSize

0.58

 Wiktionnaire

0.57

Activations Density 2.335%

words related to evaluation and outcomes in research contexts

No Comments

No Known Activations