INDEX

Explanations

specific technical details about product features and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Burnett

-0.66

EndContext

-0.62

asn

-0.54

+#+#

-0.54

 tablecloth

-0.54

 Hughes

-0.53

TestBed

-0.52

nesty

-0.49

HandlerContext

-0.49

 Sext

-0.48

POSITIVE LOGITS

 shoe

1.89

 shoes

1.83

 footwear

1.77

 Shoe

1.70

 Shoes

1.62

 Footwear

1.58

shoe

1.57

 foot

1.57

Shoe

1.56

 Foot

1.50

Activations Density 0.304%

specific technical details about product features and specifications

No Comments

No Known Activations

specific technical details about product features and specifications

No Comments

No Known Activations