INDEX

Explanations

terms related to decision-making and classification algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

mybatisplus

-0.65

Kjelder

-0.55

uxxxx

-0.55

boxylic

-0.53

ंदीखरीदारी

-0.53

 estimés

-0.53

ctivité

-0.52

ípios

-0.49

 crossorigin

-0.48

 bağlantılar

-0.48

POSITIVE LOGITS

 fuzzy

0.92

 Fuzzy

0.85

Fuzzy

0.80

fuzzy

0.75

rule

0.66

 Decision

0.66

 expert

0.66

uzzy

0.66

Decision

0.65

 Demp

0.65

Activations Density 0.383%

terms related to decision-making and classification algorithms

No Comments

No Known Activations