INDEX

Explanations

mathematical expressions, particularly inequalities and properties related to positive or non-negative quantities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TagMode

-0.56

springframework

-0.52

 FetchType

-0.52

poons

-0.51

mos

-0.51

 Styles

-0.50

UIN

-0.50

 ActivatedRoute

-0.50

vec

-0.50

Искәрмәләр

-0.48

POSITIVE LOGITS

 propOrder

0.87

rrggbb

0.81

wiſe

0.69

 leaſt

0.69

 Majefty

0.67

TagHelper

0.67

 Monfieur

0.66

 ſeveral

0.66

 becauſe

0.65

 magasiner

0.64

Activations Density 0.755%

mathematical expressions, particularly inequalities and properties related to positive or non-negative quantities

No Comments

No Known Activations