INDEX

Explanations

references to land area measurements, specifically in acres

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

fly

-0.58

Pyx

-0.54

String

-0.53

가

-0.53

ठ

-0.52

si

-0.52

aarrggbb

-0.51

toPromise

-0.51

-0.50

vand

-0.50

POSITIVE LOGITS

 acres

3.11

 acre

2.56

acre

2.33

 Acres

2.32

acres

2.13

 acreage

1.99

 Acre

1.98

Acres

1.97

Acre

1.81

 hectares

1.74

Activations Density 0.058%

references to land area measurements, specifically in acres

No Comments

No Known Activations