INDEX

Explanations

formal or legal terminology related to assessments and evaluations

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

Various textual content, ranging from scientific notes to legal documents, featuring distinct identifiers or markers indicating categories or transitions in information.

eleuther_acts_top20 · gpt-4o-mini Triggered by @johnny

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Shakspeare

-0.72

 Anſ

-0.58

InSection

-0.58

bbene

-0.57

 anastom

-0.56

 tetanus

-0.56

ly

-0.56

 Reſ

-0.55

 Houſe

-0.55

 Neander

-0.54

POSITIVE LOGITS

<bos>

0.96

XmlAccessType

0.92

the

0.81

it

0.79

0.78

Šaltiniai

0.78

httphttps

0.76

its

0.73

Искәрмәләр

0.70

">//

0.69

Activations Density 0.641%

formal or legal terminology related to assessments and evaluations

Various textual content, ranging from scientific notes to legal documents, featuring distinct identifiers or markers indicating categories or transitions in information.

No Comments

No Known Activations