INDEX

Explanations

variations of the word "swim" or its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Solano

-0.87

 Potsdam

-0.76

(":");

-0.73

 Kopi

-0.73

 Klon

-0.72

zbęd

-0.72

 piedi

-0.69

 fotografico

-0.69

 Bingham

-0.68

 Filip

-0.67

POSITIVE LOGITS

Sw

1.91

Sw

1.78

sw

1.71

sw

1.70

 Swain

1.47

SW

1.46

 Swanson

1.32

SW

1.31

Swish

1.26

 Swartz

1.18

Activations Density 0.095%

variations of the word "swim" or its derivatives

No Comments

No Known Activations