INDEX

Explanations

references to inaccuracies or errors in responses

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

 Révolution

-0.57

 Heron

-0.54

 heron

-0.53

 casquette

-0.52

 Keenan

-0.47

 Dian

-0.46

 boisson

-0.46

 poitrine

-0.46

OutputPath

-0.45

 Cochran

-0.45

POSITIVE LOGITS

 Bane

0.83

 Dine

0.82

DCE

0.82

bane

0.81

 Cline

0.81

 Vane

0.80

 Dane

0.80

 Tate

0.79

 Bate

0.79

MCE

0.79

Activations Density 2.596%

references to inaccuracies or errors in responses

No Comments

No Known Activations