INDEX

Explanations

indicators of a structured format or organization, primarily in contexts such as articles or listings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

so

-0.54

assertRaises

-0.52

достатки

-0.51

geon

-0.47

MessageTagHelper

-0.47

in

-0.45

 ří

-0.44

apimachinery

-0.43

So

-0.43

POSITIVE LOGITS

 beginnetje

0.95

Autoritní

0.87

 autorytatywna

0.83

 Roskov

0.76

 AssemblyCulture

0.75

 pinulongan

0.72

 Infórmanos

0.71

 ComVisible

0.70

 CURIAM

0.66

 actionMode

0.65

Activations Density 0.400%

indicators of a structured format or organization, primarily in contexts such as articles or listings

No Comments

No Known Activations