INDEX

Explanations

indicators of relationships and categories in various contexts, especially in scientific and medical discussions

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

pherals

-0.50

Bakgrunnsstoff

-0.46

 seguido

-0.45

 fubject

-0.43

 ſon

-0.41

Referencer

-0.41

RetentionPolicy

-0.41

 ſie

-0.40

äldrar

-0.40

 dije

-0.40

POSITIVE LOGITS

 ब्रेकडाउन

0.48

 Normdatei

0.42

:✨

0.41

MeasureSpec

0.40

($__

0.40

тли

0.40

aarrggbb

0.39

 remote

0.39

Bor

0.39

makeText

0.38

Activations Density 0.743%

indicators of relationships and categories in various contexts, especially in scientific and medical discussions

No Comments

No Known Activations