INDEX

Explanations

complex relationships and classifications within medical or psychological conditions

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

Ārējās

-0.48

 onCreateView

-0.46

 inicial

-0.43

ChromeDriver

-0.43

Referencies

-0.42

archiwizowane

-0.42

iança

-0.42

 remembrance

-0.41

 propOrder

-0.40

ambilan

-0.40

POSITIVE LOGITS

 blurring

0.51



0.48

 overlap

0.46

 definitions

0.46

 boundaries

0.46

 overlaps

0.45

 crossover

0.42

 flexible

0.42

 mixing

0.42

 blending

0.41

Activations Density 0.595%

complex relationships and classifications within medical or psychological conditions

No Comments

No Known Activations