INDEX

Explanations

terms related to bids and stretching actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Portale

-0.56

RegressionTest

-0.51

ɵɵelementStart

-0.51

ruptedException

-0.50

uppa

-0.48

 Decker

-0.48

rific

-0.48

tableFuture

-0.48

../../

-0.47

personalized

-0.46

POSITIVE LOGITS

bid

0.85

 bids

0.84

 fits

0.69

 stretch

0.68

fit

0.67

 Fits

0.64

 Bids

0.63

 Stretch

0.63

Stretch

0.63

stretch

0.62

Activations Density 0.252%

terms related to bids and stretching actions

No Comments

No Known Activations