INDEX

Explanations

elements and relationships within technical specifications or formal definitions

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

 consultato

-0.52

 functional

-0.47

 оригіналу

-0.46

tonode

-0.46

RTLI

-0.44

functional

-0.44

 burst

-0.44

bujete

-0.43

expandindo

-0.43

diad

-0.42

POSITIVE LOGITS

 AssemblyCulture

0.47

esercito

0.46

enderror

0.40

okości

0.39

ercito

0.38

 finnas

0.36

 território

0.36

ocz

0.36

 ErrIntOverflow

0.35

 navideñas

0.34

Activations Density 0.840%

elements and relationships within technical specifications or formal definitions

No Comments

No Known Activations