INDEX

Explanations

technical terms related to command line operations and configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

 Jarvis

-0.43

dermal

-0.38

kot

-0.38

acy

-0.36

 geraten

-0.36

 Spiro

-0.35

umat

-0.35

 Greek

-0.35

unknownFields

-0.35

 protoimpl

-0.35

POSITIVE LOGITS

 Glance

0.60

 glance

0.53

 wikipagina

0.52

 oslo

0.51

 nova

0.48

AutoScale

0.47

 masak

0.47

 keystone

0.45

 flavor

0.45

BeginInit

0.45

Activations Density 0.373%

technical terms related to command line operations and configurations

No Comments

No Known Activations