INDEX

Explanations

references to something previously mentioned, particularly in academic or formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 myſelf

-0.62

 pleaſure

-0.62

AnchorStyles

-0.57

 ſche

-0.54

ISupport

-0.54

thâu

-0.54

 ſta

-0.53

PerformLayout

-0.53

 layui

-0.53

 gasket

-0.52

POSITIVE LOGITS

 latter

0.78

latter

0.56

 letz

0.52

 Latter

0.52

 former

0.50

后者

0.47

 Послед

0.46

 laatste

0.45

 last

0.43

 letzter

0.40

Activations Density 0.448%

references to something previously mentioned, particularly in academic or formal contexts

No Comments

No Known Activations