INDEX

Explanations

references to sorting and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Beasley

-0.77

inquirer

-0.65

Diam

-0.64

<h4>

-0.63

eventName

-0.61

 glyphicon

-0.60

syk

-0.60

 kív

-0.59

leistung

-0.59

mycin

-0.59

POSITIVE LOGITS

 SORT

1.33

 Sorting

1.32

 sorts

1.17

 Sort

1.15

sorting

1.14

 sorting

1.14

SORT

1.05

 Kort

0.99

Sort

0.99

 sorted

0.97

Activations Density 0.063%

references to sorting and related terms

No Comments

No Known Activations