INDEX

Explanations

user experiences and advice related to product use and preferences

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

ThroughAttribute

-0.42



-0.40

PerformLayout

-0.40

ⓘ

-0.38

 Obrador

-0.38

StoryboardSegue

-0.37

GEBURTSDATUM

-0.37

 voeren

-0.37

 échou

-0.36

 drapeau

-0.36

POSITIVE LOGITS

 buying

0.75

 purchasing

0.66

 purchase

0.66

 buys

0.66

 bought

0.65

 purchased

0.65

 Buying

0.64

 purchases

0.63

Buying

0.60

 Bought

0.59

Activations Density 0.326%

user experiences and advice related to product use and preferences

No Comments

No Known Activations