INDEX

Explanations

references to sand in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ⓧ

-0.75

Goi

-0.72

Klu

-0.69

 Beale

-0.67

 Sprung

-0.66

clerview

-0.65

 felix

-0.63

Rol

-0.63

eigen

-0.62

<!--[

-0.62

POSITIVE LOGITS

 Sand

2.43

 sand

2.39

Sand

2.35

 SAND

2.13

sand

1.99

SAND

1.96

 sands

1.78

 Sands

1.55

 Sander

1.48

 Sandberg

1.47

Activations Density 0.087%

references to sand in various contexts

No Comments

No Known Activations